Commit Graph

1013 Commits

Author SHA1 Message Date
Xuan Son Nguyen
91f8ad167d
Server: version bump for httplib and json (#6169)
* server: version bump for httplib and json

* fix build

* bring back content_length
2024-03-20 13:30:36 +01:00
Georgi Gerganov
bc0baab2ea
server : allow to override -ngl in tests (#6170) 2024-03-20 14:14:32 +02:00
Georgi Gerganov
d795988d9e
Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)"
This reverts commit f8c4e745e1.
2024-03-20 13:29:49 +02:00
Ziang Wu
f8c4e745e1
llava : add a MobileVLM_V2-1.7B backup (#6152)
* Add MobileVLM_V2 backup

* Update MobileVLM-README.md

* Update examples/llava/MobileVLM-README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/llava/convert-image-encoder-to-gguf.py

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* clip :  fix whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-20 13:20:37 +02:00
Karthick
47cc7a7bf9
Server: Handle n_keep parameter in the request (#6174) 2024-03-20 12:02:34 +01:00
Jared Van Bortel
bd60d82d0c
server tests : more pythonic process management; fix bare except: (#6146)
* server tests : remove seemingly redundant newlines in print()

* server tests : use built-in subprocess features, not os.kill and psutil

* server tests : do not catch e.g. SystemExit; use print_exc

* server tests: handle TimeoutExpired exception

* server tests: fix connect on dual-stack systems

* server: tests: add new tokens regex on windows generated following new repeat penalties default changed in (#6127)

* server: tests: remove the hack on windows since now we get the good socket family

* server: tests: add new tokens regex following new repeat penalties default changed in (#6127)

* server: tests: add new tokens regex following new repeat penalties default changed in (#6127)

---------

Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-03-20 06:33:49 +01:00
Neo Zhang Jianyu
6c0b287748
update readme sycl for new update (#6151)
* update readme sycl for new update

* Update README-sycl.md

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* Update README-sycl.md

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* Update README-sycl.md

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* Update README-sycl.md

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* Update README-sycl.md

Co-authored-by: AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>

* Update README-sycl.md

Co-authored-by: AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>

* update by review comments

* update w64devkit link

* update for verify device id part

* Update README-sycl.md

Co-authored-by: Meng, Hengyu <airdldl@163.com>

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
Co-authored-by: AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>
Co-authored-by: Meng, Hengyu <airdldl@163.com>
2024-03-20 11:21:41 +08:00
DAN™
d8b009a945
Remove undeed header file. (#6158) 2024-03-19 17:16:09 +01:00
Pierrick Hymbert
d0d5de42e5
gguf-split: split and merge gguf per batch of tensors (#6135)
* gguf-split: split and merge gguf files per tensor

* gguf-split: build with make toolchain

* gguf-split: rename `--split-tensors-size` to `--split-max-tensors`. Set general.split_count KV to all split

* split : minor style + fix compile warnings

* gguf-split: remove --upload not implemented

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-19 12:05:44 +01:00
Felix
104f5e0fc1
clip : fix memory leak (#6138) 2024-03-18 17:40:22 +02:00
slaren
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
* backend : offload large batches to GPU

* fix hip

* code cleanup

* fix CUDA split buffers

* Update ggml-backend-impl.h

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix memset without set_device

* imatrix : remove sched affix from weight names

* sched : add a new split if the current one has too many inputs
reduce max inputs per split
more cleanup

* update backends

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2024-03-18 11:03:04 +01:00
Pierrick Hymbert
d01b3c4c32
common: llama_load_model_from_url using --model-url (#6098)
* common: llama_load_model_from_url with libcurl dependency

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-17 19:12:37 +01:00
Daniel Bevenius
b5f4ae09c3
gritlm : add initial README.md (#6086)
* gritlm: add initial README.md to examples/gritlm

This commit adds a suggestion for an initial README.md for the gritlm
example.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! gritlm: add initial README.md to examples/gritlm

Use the `scripts/hf.sh` script to download the model file.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! gritlm: add initial README.md to examples/gritlm

Fix editorconfig-checker error in examples/gritlm/README.md.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-03-16 17:46:29 +02:00
Ting Lou
4e9a7f7f7f
llava : change API to pure C style for Rust FFI bindgen (#6079)
Co-authored-by: Lou Ting <louting.t@alibaba-inc.com>
2024-03-15 16:31:05 +02:00
Neo Zhang Jianyu
46acb36767
fix set main gpu error (#6073) 2024-03-15 18:53:53 +08:00
slaren
b0bc9f4a9d
llama-bench : use random tokens to improve accuracy with mixtral (#6069) 2024-03-15 10:22:24 +02:00
Steve Grubb
6e0438da3c
gguf : fix resource leaks (#6061)
There several places where a gguf context is allocated. A call to gguf_free
is missing in some error paths. Also on linux, llama-bench was missing a
fclose.
2024-03-14 20:29:32 +02:00
Georgi Gerganov
044ec4b2a5
embedding : add EOS token if not present (#899) 2024-03-14 15:14:14 +02:00
Jian Liao
15a333260a
readme : improve readme for Llava-1.6 example (#6044)
Co-authored-by: Jian Liao <jianliao@adobe.com>
2024-03-14 13:18:23 +02:00
Pierrick Hymbert
43241adf22
server: disable debug release type sanitizer, simplify trigger (#6047)
- increase time out for server
 - do not fail fast
2024-03-14 13:15:39 +02:00
Georgi Gerganov
68265ebfc6
embedding : print all resulting embeddings (#899) 2024-03-14 12:37:20 +02:00
Georgi Gerganov
0fd6c1f015
embedding : print cosine similarity (#899) 2024-03-14 10:12:29 +02:00
slaren
f30ea47a87
llama : add pipeline parallelism support (#6017)
* llama : add pipeline parallelism support for batch processing with multiple CUDA GPUs

ggml-ci

* server : add -ub, --ubatch-size parameter

* fix server embedding test

* llama : fix Mamba inference for pipeline parallelism

Tested to work correctly with both `main` and `parallel` examples.

* llama : limit max batch size to n_batch

* add LLAMA_SCHED_MAX_COPIES to configure the number of input copies for pipeline parallelism
default increase to 4 (from 2)

changing this value may improve performance for some systems, but increases memory usage

* fix hip build

* fix sycl build (disable cpy_tensor_async)

* fix hip build

* llama : limit n_batch and n_ubatch to n_ctx during context creation

* llama : fix norm backend

* batched-bench : sync after decode

* swiftui : sync after decode

* ggml : allow ggml_get_rows to use multiple threads if they are available

* check n_ubatch >= n_tokens with non-casual attention

* llama : do not limit n_batch to n_ctx with non-casual attn

* server : construct batch with size of llama_n_batch

* ggml_backend_cpu_graph_compute : fix return value when alloc fails

* llama : better n_batch and n_ubatch comment

* fix merge

* small fix

* reduce default n_batch to 2048

---------

Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-13 18:54:21 +01:00
Xuan Son Nguyen
99b71c068f
Server: Use multi-task for embeddings endpoint (#6001)
* use multitask for embd endpoint

* specify types

* remove redundant {"n_predict", 0}
2024-03-13 11:39:11 +01:00
Georgi Gerganov
05b06210c9
llama : more consistent names of count variables (#5994)
* llama : more consistent names of count variables

ggml-ci

* llama : n_parallel -> n_seq_max

* common : fix param name

* examples : fix param name
2024-03-11 17:49:47 +02:00
Jakub N
828defefb6
Update server docker image URLs (#5997) 2024-03-11 14:40:42 +01:00
Xuan Son Nguyen
caa106d4e0
Server: format error to json (#5961)
* server: format error to json

* server: do not crash on grammar error

* fix api key test case

* revert limit max n_predict

* small fix

* correct coding style

* update completion.js

* launch_slot_with_task

* update docs

* update_slots

* update webui

* update readme
2024-03-11 10:56:41 +01:00
Minsoo Cheong
332bdfd798
server : maintain chat completion id for streaming responses (#5988)
* server: maintain chat completion id for streaming responses

* Update examples/server/utils.hpp

* Update examples/server/utils.hpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-11 10:09:32 +02:00
Dean
7ab7b733bb
android : fix utf8 decoding error (#5935)
* examples: fix utf8 decoding error

some models have a tokenizer that decodes an id into an incomplete utf8 sequence, need to validate and wait for next token
one example would be: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q4_0.gguf and and an example of the token is 18137

* android : minor

---------

Co-authored-by: zhangfuwen <zhangfuwen@foxmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-10 22:03:17 +02:00
Pierrick Hymbert
fa8a809a91
server: ci: windows build and tests (#5968)
* server: ci: windows build and tests

* server: ci: remove tmp push branch

* server: ci: EOF EOL

* Use builti

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* server: tests: server graceful shutdown, then kill, then hard kill

* server: tests: remove python2 unicode string

* server: tests: remove wrong comment on server starting,  close_fds is always true

* server: tests: server kill, if pid exists

* server: tests: remove dependency to killall

* server: tests: ci windows: pid exists better handling

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2024-03-10 18:17:47 +01:00
DAN™
bcebd7dbf6
llama : add support for GritLM (#5959)
* add gritlm example

* gritlm results match

* tabs to spaces

* comment out debug printing

* rebase to new embed

* gritlm embeddings are back babeee

* add to gitignore

* allow to toggle embedding mode

* Clean-up GritLM sample code.

* Fix types.

* Flush stdout and output ending newline if streaming.

* mostly style fixes; correct KQ_mask comment

* add causal_attn flag to llama_cparams

* gritml : minor

* llama : minor

---------

Co-authored-by: Douglas Hanley <thesecretaryofwar@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-10 17:56:30 +02:00
Pierrick Hymbert
621e86b331
server: benchmark: chat/completions scenario and other llm servers comparison (#5941)
* server: bench: Init a bench scenario with K6
See #5827

* server: bench: EOL EOF

* server: bench: PR feedback and improved k6 script configuration

* server: bench: remove llamacpp_completions_tokens_seconds as it include prompt processing time and it's misleading

server: bench: add max_tokens from SERVER_BENCH_MAX_TOKENS

server: bench: increase truncated rate to 80% before failing

* server: bench: fix doc

* server: bench: change gauge custom metrics to trend

* server: bench: change gauge custom metrics to trend
server: bench: add trend custom metrics for total tokens per second average

* server: bench: doc add an option to debug http request

* server: bench: filter dataset too short and too long sequences

* server: bench: allow to filter out conversation in the dataset based on env variable

* server: bench: fix assistant message sent instead of user message

* server: bench: fix assistant message sent instead of user message

* server : add defrag thold parameter

* server: bench: select prompts based on the current iteration id not randomly to make the bench more reproducible

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 23:41:49 +01:00
Georgi Gerganov
77d1ac7e00
server : print chat template info 2024-03-09 22:04:00 +02:00
slaren
d894f352bf
perplexity : support using multiple sequences to allow larger batch sizes (#5946)
* perplexity : support using multiple sequences to allow larger batch sizes

ggml-ci

* set cparams.n_parallel to the number of sequences

* print tested n_ctx, add assert
2024-03-09 19:55:54 +01:00
Georgi Gerganov
58308a0ecc
server : fix metrics init (#5964) 2024-03-09 17:34:15 +02:00
Georgi Gerganov
5b09797321
ggml : remove old quantization functions (#5942)
* ggml : remove old quantization functions

ggml-ci

* ggml : simplify ggml_quantize_chunk

ggml-ci

* ggml : restrict correctness

ggml-ci

* ggml : remove hist data from the quantization API

ggml-ci

* tests : remove hist usage in test-backend-ops

ggml-ci

* vulkan : remove hist and fix typo
2024-03-09 15:53:59 +02:00
Georgi Gerganov
97c09585d6
server : clarify some items in the readme (#5957)
* server : clarify some items in the readme

* server : fix typo
2024-03-09 15:47:47 +02:00
SeungWon Jeong
fb215c3832
server : normalize embeddings (#5956)
* output normalize embedding in '/v1/embeddings'

* common : reuse llama_embd_normalize

* common : better normalize impl

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 14:27:58 +02:00
Alexey Parfenov
0db32beaf0
server : fix passing prompt as tokens (#5955)
* server: fix passing prompt as tokens

* Update examples/server/server.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 13:16:53 +02:00
Georgi Gerganov
9674aaf35c
server : simplify logic for empty prompts (#5953) 2024-03-09 12:34:18 +02:00
Xuan Son Nguyen
950ba1ab84
Server: reorganize some http logic (#5939)
* refactor static file handler

* use set_pre_routing_handler for validate_api_key

* merge embedding handlers

* correct http verb for endpoints

* fix embedding response

* fix test case CORS Options

* fix code style
2024-03-09 11:27:53 +01:00
Gabe Goodhart
e1fa9569ba
server : add SSL support (#5926)
* add cmake build toggle to enable ssl support in server

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* add flags for ssl key/cert files and use SSLServer if set

All SSL setup is hidden behind CPPHTTPLIB_OPENSSL_SUPPORT in the same
way that the base httlib hides the SSL support

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* Update readme for SSL support in server

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* Add LLAMA_SERVER_SSL variable setup to top-level Makefile

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
2024-03-09 11:57:09 +02:00
Pierrick Hymbert
fd72d2d2a5
server: tests: add truncated prompt tests, better kv cache size (#5933)
* server: tests: add truncated prompt tests, better size

* server, tests : update regex

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-09 11:30:04 +02:00
compilade
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
* mamba : begin working on support for Mamba SSM

* mamba : begin figuring out how to (ab)use the kv cache for Mamba

* mamba : recurrent inference almost works, but incoherent

* mamba : recurrent inference WORKS!!!

* convert : optionally use d_conv and d_state from config.json for Mamba

* mamba : refactor recurrent conv, resulting in 20% perf increase

It's still slower than I'd like, but I did not really optimize `ggml_exp` yet.

I also refactored `ggml_exp` to work with tensors with more than 2 dimensions.

* ggml : parallelize ggml_exp

This results in 8% faster token generation for Mamba-130M.

* mamba : simplify the conv step with a self-overlapping view

Turns out the conv_state can be made smaller by one column.
Note that this breaks existing GGUFs of Mamba,
because the key_value_length field is tied to the conv_state size.

Convolution with a self-overlapping view is cool!
And it's much simpler than what I initially thought would be necessary
to make the convolution step work with more than 1 token at a time.

Next step is to make the SSM step work on batches of tokens too,
and thus I need to figure out a way to make a parallel selective scan
which will keep the ssm_state small and won't make it bigger
by a factor of (n_layer * batch_size).

* llama : fix Mamba KV self size wrongly displaying as f16 instead of f32

Relatedly, I also tried to see if other types than f32 worked for the states,
but they don't, because of the operators used.
It's probably better anyway to keep lots of precision there,
since the states are small anyway.

* mamba : fix self-overlapping view depth stride

* mamba : handle batches of more than 1 token

This means running Mamba no longer crashes when using the default settings!
And probably also slightly faster prompt processing.
Both batched and non-batched processing yield the same output.

Previously, the state was not cleared when starting a sequence.
Next step is to make the KV cache API work as expected for Mamba models.

* ggml: add ggml_ssm_scan to help with parallel selective scan

If the selective scan was implemented without a custom operator,
there would be waaay too many nodes in the graph. For example,
for Mamba-130M, with a batch size of 512 (the default),
a naive selective scan could add at least 24*512=12288 nodes,
which is more than LLAMA_MAX_NODES (8192),
and that's only for the smallest Mamba model.
So it's much cleaner with a custom operator.
Not sure about the name, though.

* ggml : in ggml_ssm_scan, merge multiple rows in the same vec operation

This will help with performance on CPU if ggml_vec_mul_f32
and ggml_vec_add_f32 are ever optimized with SIMD.

* mamba : very basic quantization support

Mostly works, but there is currently no difference
between the variants of a k-quant (e.g. Q4_K_S and Q4_K_M are the same).
Most of the SSM-specific weights can be kept in f32 without affecting
the size that much, since they are relatively small.
(the linear projection weights are responsible for most of Mamba's size)

Too much quantization seems to make the state degrade quite fast, and
the model begins to output gibberish.
It seems to affect bigger models to a lesser extent than small models,
but I'm not sure by how much.

Experimentation will be needed to figure out which weights are more important
for the _M (and _L?) variants of k-quants for Mamba.

* convert : fix wrong name for layer norm weight of offical Mamba models

I was using Q-bert/Mamba-* models before, which have a slighlty different
naming scheme for the weights.
(they start with "model.layers" instead of "backbone.layers")

* mamba : fuse more steps of the SSM scan in the ggml_ssm_scan operator

This increases performance on CPU by around 30% for prompt processing,
and by around 20% for text generation.

However, it also makes the ggml_exp and ggml_soft_plus operators unused.
Whether or not they should be kept will be decided later.

* convert : for Mamba, also consider the "MambaLMHeadModel" arch name

It's the name of the class of the official implementation,
though they don't use it (yet) in the "architectures" field of config.json

* mamba : fix vocab size problems with official models

The perplexity was waaaay to high for models with a non-round vocab size.
Not sure why, but it needed to be fixed in the metadata.

Note that this breaks existing GGUF-converted Mamba models,
but **only if** the vocab size was not already rounded.

* ggml : remove ggml_exp and ggml_soft_plus

They did not exist anyway outside of this branch,
and since ggml_ssm_scan fused operations together, they are unused.
It's always possible to bring them back if needed.

* mamba : remove some useless comments

No code change.

* convert : fix flake8 linter errors

* mamba : apply suggestions from code review

* mamba : remove unecessary branch for row-wise ssm_state and C multiplication

It was previously done to avoid permuting when only one token is processed
at a time (like when generating text), but permuting is cheap,
and dynamically changing the compute graph is not future-proof.

* ggml : in ggml_ssm_scan, use more appropriate asserts

* ggml : rename the destination pointer in ggml_compute_forward_ssm_scan_f32

* mamba : multiple sequences, but one at a time

This is a step towards making this Mamba implementation usable
with the server example (the way the system prompt is kept when clearing
the client slots will need to be changed before this can work, though).

The KV cache size for this kind of model is tied to the maximum number
of sequences kept at any single time.
For now, this number is obtained from n_parallel (plus one,
to have an extra sequence to dedicate to the system prompt),
but there might be a better way to do this which won't also
make the main example use 2 cells even if only 1 is really used.
(for this specific case, --parallel 0 helps)

Simultaneous sequence processing will probably require changes to
ggml_ssm_scan, and possibly a new operator for the conv step.

* mamba : support llama_kv_cache_seq_cp

This (mis)uses the logic around K shifts, because tokens in a state
can't be shifted anyway, and because inp_K_shift has the right shape and type.
Using ggml_get_rows is a nice way to do copies, but copy chains can't work.
Fortunately, copy chains don't really seem to be used in the examples.

Each KV cell is dedicated to the sequence ID corresponding to its own index.

* mamba : use a state mask

It's cleaner than the previous heuristic of
checking for the pos of the first token in the batch.

inp_KQ_mask could not be re-used for this, because it has the wrong shape
and because it seems more suited to the next step of
simultaneous sequence processing (helping with the problem of
remembering which token belongs to which sequence(s)/state(s)).

* llama : replace the usage of n_ctx with kv_self.size in many places

* mamba : use n_tokens directly instead of n_tok

* mamba : in comments, properly refer to KV cells instead of slots

* mamba : reduce memory usage of ggml_ssm_scan

From 290.37 MiB to 140.68 MiB of CPU compute buffer size
with Mamba 3B with a batch size of 512.

The result tensor of ggml_ssm_scan was previously a big part
of the CPU compute buffer size. To make it smaller,
it does not contain the intermediate ssm states anymore.
Both y and the last ssm state are combined in the result tensor,
because it seems only a single tensor can be returned by an operator
with the way the graph is built.

* mamba : simultaneous sequence processing

A batch can now contain tokens from multiple sequences.

This is necessary for at least the parallel example, the server example,
and the HellaSwag test in the perplexity example.

However, for this to be useful, uses of llama_kv_cache_seq_rm/cp
will need to be changed to work on whole sequences.

* ggml : add ggml_ssm_conv as a new operator for the conv step of Mamba

This operator makes it possible to use and update the correct states
for each token of the batch in the same way as ggml_ssm_scan.
Other solutions which use existing operators would need loops which would
add too many nodes to the graph (at least the ones I thought of).

Using this operator further reduces the size of the CPU compute buffer
from 140.68 MiB to 103.20 MiB with Mamba 3B with a batch size of 512.
And (at least on CPU), it's a bit faster than before.

Note that "ggml_ssm_conv" is probably not the most appropriate name,
and it could be changed if a better one is found.

* llama : add inp_s_seq as a new input tensor

The most convenient implementation to select the correct state (for Mamba)
for each token is to directly get the correct index from a tensor.
This is why inp_s_seq is storing int32_t and not floats.

The other, less convenient way to select the correct state would be
to have inp_KQ_mask contain 1.0f for each state used by a token
and 0.0f otherwise. This complicates quickly fetching the first used
state of a token, and is also less efficient because a whole row
of the mask would always need to be read for each token.

Using indexes makes it easy to stop searching when there are
no more sequences for a token, and the first sequence assigned
is always very quickly available (it's the first element of each row).

* mamba : support llama_kv_cache_seq_cp copy chains

* mamba : support shifting and dividing the kv cache pos

* mamba : make the server and parallel examples work with whole sequences

A seq_id is dedicated to the system prompt in both cases.

* llama : make llama_kv_cache_seq_rm return whether it succeeded or not

* mamba : dedicate an input tensor for state copy indices

This is cleaner and makes it easier to adapt when/if token positions
(and by extension, inp_K_shift) are no longer integers.

* mamba : adapt perplexity, batched, and batched-bench examples

* perplexity : limit the max number of sequences

This adapts to what the loaded model can provide.

* llama : add llama_n_max_seq to get the upper limit for seq_ids

Used by the perplexity example.

* batched : pass n_parallel to the model's context params

This should have been there already, but it wasn't.

* batched-bench : reserve sequences to support Mamba

* batched-bench : fix tokens being put in wrong sequences

Generation quality isn't what's measured in there anyway,
but at least using the correct sequences avoids using non-consecutive
token positions.

* mamba : stop abusing attention metadata

This breaks existing converted-to-GGUF Mamba models,
but will allow supporting mixed architectures like MambaFormer
without needing to break Mamba models.

This will also allow changing the size of Mamba's states
without having to reconvert models in the future.
(e.g. using something else than d_conv - 1 columns for the conv_states
 will not require breaking existing converted Mamba models again)

* gguf-py : add new KV metadata key-value pairs for Mamba

* llama : add new metadata key-value pairs for Mamba

* llama : guard against divisions by zero when n_head is 0

* mamba : rename "unlimited" KV cache property to "recurrent"

* mamba : more correctly update the "used" field of the KV cache

* ggml : in ggml_ssm_scan, use a threshold for soft_plus

This is how the official Mamba implementation does it,
and it's also what torch.nn.Softplus does.

* convert : for Mamba, fallback to internal NeoX tokenizer

The resulting models are exactly the same
as if the tokenizer.json and tokenizer_config.json of GPT-NeoX were there.

* mamba : support state saving and restoring

* ggml : implicitly pass src tensors through dst for Mamba-related ops

* mamba : clarify some comments

* server : fix cache_tokens not getting correctly resized

Otherwise, when the "we have to evaluate at least 1 token" special case
was triggered, an extra token was kept in cache_tokens even if it was
removed from the KV cache.

For Mamba, this caused useless prompt reprocessing when the previous
request triggered the above case.

* convert-hf : support new metadata keys for Mamba

For the models available at
https://huggingface.co/collections/state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406

* mamba : rename metadata to be more similar to transformers library

This breaks existing converted-to-GGUF models,
but the metadata names are more "standard".

* mamba : support mamba-*-hf models

These models share their token_embd.weight with their output.weight

* mamba : add missing spaces

This is purely a formatting change.

* convert-hf : omit output.weight when identical with token_embd.weight

Only for Mamba for now, but it might be relevant for other models eventually.
Most Mamba models actually share these two tensors, albeit implicitly.

* readme : add Mamba to supported models, and add recent API changes

* mamba : move state_seq and state_mask views outside layer loop

A few tensors were also missing `struct` in front of `ggml_tensor`.
2024-03-08 17:31:00 -05:00
Pierrick Hymbert
76e868821a
server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix values cast to int. Add Process-Start-Time-Unix header. (#5937)
Closes #5850
2024-03-08 12:25:04 +01:00
Georgi Gerganov
af37fd8b30
server : fix EOS token detection with disabled cache (#5938) 2024-03-08 12:40:02 +02:00
Georgi Gerganov
6cdabe6526
llama-bench : add embeddings option (#5924)
* llama-bench : add embeddings option

* llama-bench : do not hard code embd default value

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-03-07 16:32:38 +02:00
Minsoo Cheong
55a2a900ff
server : add /v1/completions endpoint (#5914)
* add-`/v1/completions`-endpoint

* add legacy comment to `/completion` endpoint
2024-03-07 12:42:39 +02:00
Georgi Gerganov
2002bc96bf
server : refactor (#5882)
* server : refactoring (wip)

* server : remove llava/clip objects from build

* server : fix empty prompt handling + all slots idle logic

* server : normalize id vars

* server : code style

* server : simplify model chat template validation

* server : code style

* server : minor

* llama : llama_chat_apply_template support null buf

* server : do not process embedding requests when disabled

* server : reorganize structs and enums + naming fixes

* server : merge oai.hpp in utils.hpp

* server : refactor system prompt update at start

* server : disable cached prompts with self-extend

* server : do not process more than n_batch tokens per iter

* server: tests: embeddings use a real embeddings model (#5908)

* server, tests : bump batch to fit 1 embedding prompt

* server: tests: embeddings fix build type Debug is randomly failing (#5911)

* server: tests: embeddings, use different KV Cache size

* server: tests: embeddings, fixed prompt do not exceed n_batch, increase embedding timeout, reduce number of concurrent embeddings

* server: tests: embeddings, no need to wait for server idle as it can timout

* server: refactor: clean up http code (#5912)

* server : avoid n_available var

ggml-ci

* server: refactor: better http codes

* server : simplify json parsing + add comment about t_last

* server : rename server structs

* server : allow to override FQDN in tests

ggml-ci

* server : add comments

---------

Co-authored-by: Pierrick Hymbert <pierrick.hymbert@gmail.com>
2024-03-07 11:41:53 +02:00
Jeffrey Quesnelle
29eee40474
fix speculative decoding build on windows (#5874) 2024-03-04 22:23:06 -05:00
Georgi Gerganov
29ae62d2ae
llama : fix embeddings (#5796)
* llama : fix embeddings

ggml-ci

* llama : do not use KV cache for non-causal models

ggml-ci

* embeddings : fix llama_batch_init arg

* llama : add pooling switch

* llama : distinguish token vs sequence embeddings

ggml-ci

* llama : assert pooling tensor

* llama : simplify causal mask condition

ggml-ci

* llama : assert input batch with pooling enabled

* readme : update API changes list
2024-03-04 22:31:20 +02:00
Minsoo Cheong
6d341ab6c5
speculative : implement stochastic speculative sampling (#5625)
* (WIP) Implement stochastic speculative decoding

* sample from residual distribution on draft accept failure

* fix #5657: force greedy sampling with probs when temp is 0

* remove p_accept parameter

* fix style

* remove unused variables

* add srand() in speculative.cpp

* replace use of rand() with mt19937 sampling

* fixes based on review (@JohannesGaessler)

* fix r random generation

* randomly select next sequence to verify + fix bug in memory freeing

* fix bug in active_seqs sync

* fix uniform int distribution initialization

* remove warnings from comparison between int and size_t

* check grammar in `llama_sample_probability_distribution_impl`

* remove malloc code by utilizing vectors

* add PR link to README
2024-03-04 20:24:00 +02:00
Xuan Son Nguyen
4ffcdce2ff
add alias for chat template (#5858) 2024-03-04 12:22:08 +01:00
DAN™
5a51cc1bb4
main : support special tokens as reverse/anti prompt (#5847)
* Support special tokens as reverse/anti prompt.

* Tokenize antiprompts only once.

* main : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-04 09:57:20 +02:00
Pierrick Hymbert
8ef969afce
server : init http requests thread pool with --parallel if set (#5836) 2024-03-03 09:48:36 +02:00
Pierrick Hymbert
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
* server: tests: add models endpoint scenario

* server: /v1/models add some metadata

* server: tests: add debug field in context before scenario

* server: tests: download model from HF, add batch size

* server: tests: add passkey test

* server: tests: add group attention params

* server: do not truncate prompt tokens if self-extend through group attention is enabled

* server: logs: do not truncate log values

* server: tests - passkey - first good working value of nga

* server: tests: fix server timeout

* server: tests: fix passkey, add doc, fix regex content matching, fix timeout

* server: tests: fix regex content matching

* server: tests: schedule slow tests on master

* server: metrics: fix when no prompt processed

* server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1

* server: tests: increase timeout for completion

* server: tests: keep only the PHI-2 test

* server: tests: passkey add a negative test
2024-03-02 22:00:14 +01:00
Jared Van Bortel
4d4d2366fc
convert : automatically fall back to HfVocab if tokenizer.model doesn't exist (#5821) 2024-03-02 12:27:26 -05:00
Neo Zhang Jianyu
715641391d
Support multiple GPUs (split mode) on SYCL backend (#5806)
* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments
2024-03-02 19:49:30 +08:00
Georgi Gerganov
38d16b1426
server : remove api_like_OAI.py proxy script (#5808) 2024-03-01 20:00:58 +02:00
Pierrick Hymbert
3ab8b3a92e
llama : cleanup unused mmq flags (#5772)
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-03-01 13:39:06 +02:00
Pierrick Hymbert
5cb02b4a01
server: allow to override threads server pool with --threads-http (#5794) 2024-03-01 10:08:08 +01:00
Georgi Gerganov
f105471ef6
server : fix newlines in help (#5785) 2024-03-01 09:59:43 +02:00
Xuan Son Nguyen
052051d8ae
Server: normalize naming (#5779)
* server: normalize naming

* fix spacing
2024-02-29 21:42:11 +01:00
Xuan Son Nguyen
a693bea1e6
server : hit Ctrl+C twice to exit (#5734)
* server: twice ctrl+C to exit

* std::atomic_flag

* sigint: message

* sigint: stderr

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2024-02-28 10:55:37 +02:00
Jorge A
efc72253f7
server : add "/chat/completions" alias for "/v1/...` (#5722)
* Add "/chat/completions" as alias for "/v1/chat/completions"

* merge to upstream master

* minor : fix trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-28 10:39:15 +02:00
Kawrakow
0becb22ac0
IQ4_XS: a 4.25 bpw quantization (#5747)
* Try IQ4_NL with blocks of 64 - does not look good

* iq4_xs: go to super-blocks of 256 and 6-bit scales for blocks of 32

* iq4_xs: CUDA works - 133.2 t/s

* iq4_xs: AVX2 dot product

* iq4_xs: ARM_NEON dot product

* iq4_nl: Metal implementation

As usual, Metal / Apple Silicon don't like my quants.

* iq3_xs: minor fix

* iq4_xs: shrink by using IQ3_S for attn_k and attn_q

* iq4_xs: revert using IQ3_S for attn_k and attn_v

PPL vs size is good, but CPU performance suffers: on M2 Max
TG-128 drops to 21.7 t/s from 28.8, and on a Ryzen-7950X
to 14.5 t/s from 15.8 t/s. On CUDA we have 135 t/s when
using IQ3_S vs 133 t/s with pure IQ4_XS.

* Fix CI

* iq4_xs: Added forgotten check for 256 divisibility

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-27 16:34:24 +02:00
Georgi Gerganov
9d533a77d0
llama : fix defrag bugs + add parameter (#5735)
* llama : fix defrag bugs + enable by default

ggml-ci

* llama : add defrag_thold parameter

ggml-ci

* llama : cont

* llama : disable log message

ggml-ci

* llama : fix graph size check during defrag
2024-02-27 14:35:51 +02:00
Xuan Son Nguyen
b11a93df41
fix server hangs on empty prompt (#5733) 2024-02-26 23:15:48 +01:00
Kawrakow
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
* Adding IQ2_S and IQ2_M as a single cumulative commit

* Update examples/quantize/quantize.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-26 18:28:38 +02:00
Pierrick Hymbert
e3965cf35a
server: tests - slow inference causes timeout on the CI (#5715)
* server: tests - longer inference timeout for CI
2024-02-25 22:48:33 +01:00
Pierrick Hymbert
8b350356b2
server: docs - refresh and tease a little bit more the http server (#5718)
* server: docs - refresh and tease a little bit more the http server

* Rephrase README.md server doc

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-25 21:46:29 +01:00
Georgi Gerganov
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
* llama : refactor k-shift implementation

ggml-ci

* llama : rename llama_kv_cache_seq_shift to llama_kv_cache_seq_add

* llama : cont k-shift refactoring + normalize type names

ggml-ci

* minor : fix MPI builds

* llama : reuse n_rot from the build context

ggml-ci

* llama : revert enum name changes from this PR

ggml-ci

* llama : update llama_rope_type

* llama : add comment about rope values

* llama : fix build

* passkey : apply kv cache updates explicitly

ggml-ci

* llama : change name to llama_kv_cache_update()

* llama : add llama_kv_cache_seq_pos_max()

* passkey : fix llama_kv_cache_seq_pos_max() usage

* llama : some llama_kv_cell simplifications

* llama : add llama_kv_cache_compress (EXPERIMENTAL)

* llama : add alternative KV cache merging (EXPERIMENTAL)

* llama : add llama_kv_cache_defrag

* llama : comments

* llama : remove llama_kv_cache_compress

will add in a separate PR

ggml-ci

* llama : defragment via non-overlapping moves

* llama : ggml_graph based defrag implementation

ggml-ci

* llama : switch the loop order in build_defrag

* llama : add comments
2024-02-25 22:12:24 +02:00
compilade
f7625019c5
server : fix crash when system prompt is bigger than batch size (#5714)
The system prompt is now decoded in batches.

* server : fix off-by-one n_past when start of prompt matches whole cache

The tokens right after the matching part would otherwise skip a pos value.
2024-02-25 20:43:50 +02:00
Radosław Gryta
abbabc5e51
ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (#5711)
* [ggml-quants] Provide ggml_vqtbl1q_u8 for 64bit compatibility

vqtbl1q_u8 is not part of arm v7 neon library

* [android-example] Remove abi filter after arm v7a fix

* [github-workflows] Do not skip Android armeabi-v7a build
2024-02-25 20:43:00 +02:00
Pierrick Hymbert
930b178026
server: logs - unified format and --log-format option (#5700)
* server: logs - always use JSON logger, add add thread_id in message, log task_id and slot_id

* server : skip GH copilot requests from logging

* server : change message format of server_log()

* server : no need to repeat log in comment

* server : log style consistency

* server : fix compile warning

* server : fix tests regex patterns on M2 Ultra

* server: logs: PR feedback on log level

* server: logs: allow to choose log format in json or plain text

* server: tests: output server logs in text

* server: logs switch init logs to server logs macro

* server: logs ensure value json value does not raised error

* server: logs reduce level VERBOSE to VERB to max 4 chars

* server: logs lower case as other log messages

* server: logs avoid static in general

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server: logs PR feedback: change text log format to: LEVEL [function_name] message | additional=data

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-25 13:50:32 +01:00
Pierrick Hymbert
d52d7819b8
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)
* server: monitoring - add /metrics prometheus compatible endpoint

* server: concurrency issue, when 2 task are waiting for results, only one call thread is notified

* server: metrics - move to a dedicated struct
2024-02-25 13:49:43 +01:00
Georgi Gerganov
ab336a9d5e
code : normalize enum names (#5697)
* coda : normalize enum names

ggml-ci

* code : cont

* code : cont
2024-02-25 12:09:09 +02:00
Pierrick Hymbert
9e359a4f47
server: continue to update other slots on embedding concurrent request (#5699)
* server: #5655 - continue to update other slots on embedding concurrent request.

* server: tests: add multi users embeddings as fixed

* server: tests: adding OAI compatible embedding concurrent endpoint

* server: tests: adding OAI compatible embedding with multiple inputs
2024-02-24 19:16:04 +01:00
Kawrakow
4c4cb30736
IQ3_S: a much better alternative to Q3_K (#5676)
* iq4_nl: squash commits for easier rebase

* Basics (quantize, dequantize)
* CUDA dequantize and dot product
* Slightly faster CUDA dot product (120 t/s)
* Switch to 6-bit scales
* Scalar dot product
* AVX2 dot product
* ARM_NEON dot product
* Works on metal, but still slow
* Slightly better Metal dot product
* Another small Metal improvement
* Metal dot product is getting there
* Faster CUDA dot product
* Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided
* Report the actual bpw
* Add _xs mix that is 4.05 bpw for non-MoE models
* Remove IQ4_XS for now, slightly adjust kvalues_iq4nl
* AVX2 dot product uses Q8_0 instead of Q8_K
* Add to test-backend-ops
* Minor fix
* Also use use Q5_K for attn_output in MoE models
* Fixes after merging latest master
* Switching to blocks of 32
* AVX2 for blocks of 32
* Scaler dot product for blocks of 32
* ARM_NEON dot product for blocks of 32
* Metal kernels for blocks of 32
* Slightly faster Metal kernels

* Resurrecting iq3_xs

After all the experimentation, nothing was better than this.

* Minor PPL improvement via a block scale fudge factor

* Minor improvement via 3 neighbours

* iq3_xs: working scalar and AVX2 dot products

* iq3_xs: ARM_NEON dot product - works but extremely slow (10 t/s)

* iq3_xs: working Metal implementation

* Adding IQ3_M - IQ3_XS mix with mostly Q4_K

* iiq3_xs: a 3.4375 bpw variant

* iq3_xs: make CUDA work for new version

* iq3_xs: make scalar and AVX2 work for new version

* iq3_s: make ARM_NEON work with new version

* iq3_xs: make new version work on metal

Performance is very similar to Q3_K_S

* iq3_xs: tiny Metal speed improvement

* iq3_xs: tiny Metal speed improvement

* Fix stupid warning

* Q3_K_XS now uses a mix of IQ3_XS and IQ3_XXS

* iq3_xs: rename to iq3_s

* iq3_s: make tests pass

* Move Q3_K_XS mix to 3.25 bpw

* Attempt to fix failing tests

* Another attempt to fix the Windows builds

* Attempt to fix ROCm

* ROCm again

* iq3_s: partial fix for QK_K = 64

* iq3_s: make it work on metal for QK_K = 64

Pleasent surprise: the coding was super-block size independent,
so all it took was to delete some QK_K == 256 guards.

* Will this fix ROCm?

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-24 16:23:52 +02:00
Pierrick Hymbert
525213d2f5
server: init functional tests (#5566)
* server: tests: init scenarios
 - health and slots endpoints
 - completion endpoint
 - OAI compatible chat completion requests w/ and without streaming
 - completion multi users scenario
 - multi users scenario on OAI compatible endpoint with streaming
 - multi users with total number of tokens to predict exceeds the KV Cache size
 - server wrong usage scenario, like in Infinite loop of "context shift" #3969
 - slots shifting
 - continuous batching
 - embeddings endpoint
 - multi users embedding endpoint: Segmentation fault #5655
 - OpenAI-compatible embeddings API
 - tokenize endpoint
 - CORS and api key scenario

* server: CI GitHub workflow


---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-24 12:28:55 +01:00
AlpinDale
fd43d66f46
server : add KV cache quantization options (#5684) 2024-02-23 21:31:54 +02:00
Xuan Son Nguyen
a46f50747b
server : fallback to chatml, add AlphaMonarch chat template (#5628)
* server: fallback to chatml

* add new chat template

* server: add AlphaMonarch to test chat template

* server: only check model template if there is no custom tmpl

* remove TODO
2024-02-22 10:33:24 +02:00
Alexey Parfenov
c5688c6250
server : clarify some params in the docs (#5640) 2024-02-22 10:27:32 +02:00
Xuan Son Nguyen
7c8bcc11dc
Add docs for llama_chat_apply_template (#5645)
* add docs for llama_chat_apply_template

* fix typo
2024-02-22 00:31:00 +01:00
Jared Van Bortel
89febfed93
examples : do not assume BOS when shifting context (#5622) 2024-02-21 10:33:54 -05:00
Pierrick Hymbert
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
* server: health: fix race condition on slots data using tasks queue

* server: health:
    * include_slots only if slots_endpoint
    * fix compile warning task.target_id not initialized.
2024-02-21 15:47:48 +01:00
Daniel Bevenius
cc6cac08e3
llava : add --skip-unknown to 1.6 convert.py (#5632)
This commit adds the `--skip-unknown` option to the convert.py script
and removes the saving of the updated checkpoints to avoid updating
possibly checked out files.

The motivation for this change is that this was done for 1.5
in Commit fc0c8d286a ("llava :
update surgery script to not remove tensors") and makes the examples
more consistent.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-21 15:36:57 +02:00
Kawrakow
a14679cc30
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)
* iq4_nl: squash commits for easier rebase

* Basics (quantize, dequantize)
* CUDA dequantize and dot product
* Slightly faster CUDA dot product (120 t/s)
* Switch to 6-bit scales
* Scalar dot product
* AVX2 dot product
* ARM_NEON dot product
* Works on metal, but still slow
* Slightly better Metal dot product
* Another small Metal improvement
* Metal dot product is getting there
* Faster CUDA dot product
* Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided
* Report the actual bpw
* Add _xs mix that is 4.05 bpw for non-MoE models
* Remove IQ4_XS for now, slightly adjust kvalues_iq4nl
* AVX2 dot product uses Q8_0 instead of Q8_K
* Add to test-backend-ops
* Minor fix
* Also use use Q5_K for attn_output in MoE models
* Fixes after merging latest master
* Switching to blocks of 32
* AVX2 for blocks of 32
* Scaler dot product for blocks of 32
* ARM_NEON dot product for blocks of 32
* Metal kernels for blocks of 32
* Slightly faster Metal kernels

* iq4_nl: Fix after merging with master

* iq4_nl: another fix after merging with master

* Use IQ4_NL instead of Q4_K when using k-quants is not possible

* Fix typo that makes several tests fail

* It was the ggml_vdotq thing missed inside the brackets

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-21 11:39:52 +02:00
CJ Pais
6560bed3f0
server : support llava 1.6 (#5553)
* server: init working 1.6

* move clip_image to header

* remove commented code

* remove c++ style from header

* remove todo

* expose llava_image_embed_make_with_clip_img

* fix zig build
2024-02-20 21:07:22 +02:00
Daniel Bevenius
4ed8e4fbef
llava : add explicit instructions for llava-1.6 (#5611)
This commit contains a suggestion for the README.md in the llava
example. The suggestion adds explicit instructions for how to convert
a llava-1.6 model and run it using llava-cli.

The motivation for this is that having explicit instructions similar to
the 1.5 instructions will make it easier for users to try this out.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-20 19:30:27 +02:00
Xuan Son Nguyen
9c405c9f9a
Server: use llama_chat_apply_template (#5593)
* server: use llama_chat_apply_template

* server: remove trailing space

* server: fix format_chat

* server: fix help message

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server: fix formatted_chat

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-20 15:58:27 +01:00
Pierrick Hymbert
c0a8c6db37
server : health endpoint configurable failure on no slot (#5594) 2024-02-20 09:48:19 +02:00
nopperl
9d679f0fcc
examples : support minItems/maxItems in JSON grammar converter (#5039)
* support minLength and maxLength in JSON schema grammar converter

* Update examples/json-schema-to-grammar.py

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-19 16:14:07 +02:00
Georgi Gerganov
1387cf60f7
llava : remove extra cont (#5587) 2024-02-19 15:23:17 +02:00
slaren
6fd413791a llava : replace ggml_cpy with ggml_cont 2024-02-19 15:09:43 +02:00
Daniel Bevenius
7084755396
llava : avoid changing the original BakLLaVA model (#5577)
This is a follup of Commit fc0c8d286a
("llava : update surgery script to not remove tensors") but this time
the change is to the BakLLaVA specific part of the surgery script.

I've been able to test this using SkunkworksAI/BakLLaVA-1 and it works
as expected using the instructions in README.md.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-19 10:31:59 +02:00
NawafAlansari
4480542b22
baby-llama : allocate graphs in ggml_context (#5573)
* Fixed the baby-llama issue (see issue #4830)

* minor : fix whitespaces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-19 10:25:38 +02:00
Georgi Gerganov
b1de96824b
ci : fix wikitext url + compile warnings (#5569)
ggml-ci
2024-02-18 22:39:30 +02:00
Robey Holderith
5ee99c32f5
common, server : surface min_keep as its own parameter (#5567)
* Feature - surface min_keep as its own parameter

* Updated README with min_keep param
2024-02-18 21:11:16 +02:00
Pierrick Hymbert
c145f8a132
server : slots monitoring endpoint (#5550) 2024-02-18 19:39:57 +02:00
Pierrick Hymbert
e75c6279d1
server : enhanced health endpoint (#5548)
* server: enrich health endpoint with available slots, return 503 if not slots are available

* server: document new status no slot available in the README.md
2024-02-18 18:31:28 +02:00
Pierrick Hymbert
36376abe05
server : --n-predict option document and cap to max value (#5549)
* server: document --n-predict

* server: ensure client request cannot override n_predict if set

* server: fix print usage LF in new --n-predict option
2024-02-18 18:30:09 +02:00
Daniel Hiltgen
66c1968f7a
server : graceful server shutdown (#5244)
This updates the server queue to support graceful shutdown of the server on signals.
2024-02-18 18:23:16 +02:00
Herman Semenov
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528) 2024-02-18 18:20:12 +02:00
Daniel Bevenius
fc0c8d286a
llava : update surgery script to not remove tensors (#5536)
This commit updates the surgery script to not remove the tensors from the
model file. For this to work the `--skip-unknown` flag is added as an
argument to the convert.py script in README.md.

The motivation for this change is that the surgery script currently
removes the projector tensors from the model file. If the model was
checked out from a repository, the model file will have been updated
and have to be checked out again to reset this effect. If this can be
avoided I think it would be preferable.

I did not perform this change for BakLLaVA models as I am not sure
how that part works.
2024-02-18 18:19:23 +02:00
Kawrakow
bd2d4e393b
1.5 bit quantization (#5453)
* iq1_s: WIP basics

* iq1_s: CUDA is working

* iq1_s: scalar CPU dot product

* iq1_s: WIP AVX2 dot product - something is not right

* Fix tests

* Fix shadow warnings

* Fix after merge with latest master

* iq1_s: AVX2 finally works

* iq1_s: ARM_NEON dot product. Works, but not very fast

* iq1_s: better grid

* iq1_s: use IQ2_XXS for attn_output

At a cost of 0.04 extra bpw this gives a big improvement in PPL.

* iq1_s: Metal basics

Dequantize works, but not dot product

* iq1_s: Metal works, but quite slow

As usual, Apple Silicon does not like the code I write.

* iq1_s: Tests

* iq1_s: slightly faster dot product

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-18 18:16:55 +02:00
Ananta Bastola
6e4e973b26
ci : add an option to fail on compile warning (#3952)
* feat(ci): add an option to fail on compile warning

* Update CMakeLists.txt

* minor : fix compile warnings

ggml-ci

* ggml : fix unreachable code warnings

ggml-ci

* ci : disable fatal warnings for windows, ios and tvos

* ggml : fix strncpy warning

* ci : disable fatal warnings for MPI build

* ci : add fatal warnings to ggml-ci

ggml-ci

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-17 23:03:14 +02:00
Herman Semenov
4cb0727698
llava : removed excess free(NULL) operation (#5531) 2024-02-16 14:43:23 +02:00
Alexey Parfenov
6dcc02d244
server : add "samplers" param to control the samplers order (#5494) 2024-02-16 13:33:25 +02:00
Rőczey Barnabás
5f5808ca7b
server : fix system prompt cli (#5516) 2024-02-16 12:00:56 +02:00
bmwl
f486f6e1e5
ggml : add numa options (#5377)
* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h

* Reverted Makefile

* Fixed include

* Removed sched.h from ggml.h, moved ggml_get_numa_affinity into ggml.c, removed trailing whitespace and fixed up a few inconsistent variables

* removed trailing whitespace

* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h

* Reverting Makefile

* Fixed a number of issues with the move from BOOL to ggml_numa_strategies. Added a note about mirror mode note being implemented yet

* Removing MIRROR_MODE code for this PR

* Removing last bit of MIRROR_MODE code for this PR

* Removing unneeded branch in server.cpp example and moving get_numa_affinity and making it static

* Fixed lingering init_llama_backend() bool calls in tests and examples

* Remote enum llama_numa_strategies

* Revert bad merge with dynatemp flags

* add missing enum ggml_numa_strategies declaration and revert sync problem with master

* add missing enum ggml_numa_strategies declaration

* fixed ggml_init_numa variable

* Update ggml.h

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update READMEs with info about numa flags, change INTERLEAVE strategy name to DISTRIBUTE everywhere, implement the improved distribution strategy from @rankaiyx, fix a spelling mistake and un-merge some bad merges

* split numa init out from llama_backend_init and created llama_numa_init. Updated all code paths and samples

* Fix up some boolean vs enum comparisons

* Added #ifdefs for non-Linux OS that don't have cpu_set_t datatype

* Update ggml.h

Align enum values

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update ggml.c

Remove whitespace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update ggml.c

align paremeters

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/server.cpp

remove whitespace and align brace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update common/common.cpp

Remove whitespace and align brace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* unified ggml_numa_strategy enum and fixed text alignment in server.cpp example

* Update ggml.c

simplified return for platforms without NUMA support

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* removed redundant else from cli argument processing of --numa

* whitespace

---------

Co-authored-by: root <root@nenya.lothlorien.ca>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-02-16 11:31:07 +02:00
Daniel Bevenius
60ed04cf82
llava : fix clip-model-is-vision flag in README.md (#5509)
* llava: fix clip-model-is-vision flag in README.md

This commit fixes the flag `--clip_model_is_vision` in README.md which
is does not match the actual flag:
```console
$ python convert-image-encoder-to-gguf.py --help
...
  --clip-model-is-vision
                        The clip model is a pure vision model
                        (ShareGPT4V vision extract for example)
```

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* llava: update link to vit config in README.md

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-16 11:24:39 +02:00
Georgi Gerganov
c06e45d729
clip : fix wrong loop condition 2024-02-15 18:49:08 +02:00
Elbios
0d4177126b
llava : fix memory management bug (#5491)
* Fix memory management in llava and server code

Fixes this error:

llama_new_context_with_model: graph splits (measure): 3
Available slots:
 -> Slot 0 - max context: 6000
{"timestamp":1707926446,"level":"INFO","function":"main","line":2623,"message":"model loaded"}
all slots are idle and system prompt is empty, clear the KV cache
slot 0 - loaded image
slot 0 is processing [task id: 0]
slot 0 : kv cache rm - [0, end)
slot 0 - encoding image [id: 1]
munmap_chunk(): invalid pointer
Aborted

* Make it cleaner by checking size in batch free wrapper
2024-02-15 10:01:57 +02:00
John
7930a8a6e8
llaba : hotfix for llava-1.6 image number (#5495)
Co-authored-by: John <cmt-nct@users.noreply.github.com>
2024-02-15 09:59:18 +02:00
John
ccbb277f46
llava : update README.md (#5489)
* Update README.md

* Update README.md

* Update examples/llava/README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-14 16:49:42 +02:00
John
aa23412989
llava : support v1.6 (#5267)
* Create llava-survery-v2.py

* Update convert-image-encoder-to-gguf.py

* Update convert-image-encoder-to-gguf.py

* Rename llava-survery-v2.py to llava-surgery-v2.py

* Update convert-image-encoder-to-gguf.py

will now search for projector

* Update convert-image-encoder-to-gguf.py

whoops

* Update llava-surgery-v2.py

* Clip: Bugfix for normalization (it did not loat the 3 std and mean values)
Clip: bicubic resize function
Clip: added save-to-bmp/pil for debugging and conversion from/to 32/8 images
Clip: added normalization with FP16 precision simulation (image tensors match HF implementation, can be switched off, only used for llava-1.6)
Clip: added newline tensor, mergetype kv, image-grid kv, new resize-pad function with resolution from gridpoints
Clip: clip_image_preprocess now returns a float * vector instead of float, this way llava 1.5 and 1.6 is supported
llava: added ggml cpu graph for embedding patching, added spatial_unpad preliminary support, added a lot of comments that need to be cleaned when all is final
convert-image-encoder: fixed image-grid flattening

* whitespace corrections

* ws

* Tensors are now properly permuted.
Before the embeddings were inserted 1:1, now they are split into the 24x24 patches as in reference.

* ws

* added verbose_prompt support into cli
added stopwords for llava-1.6 into cli

* moved llava functions to llava.cpp, made clip.h C compatible API, replaced vector style functions with pointers, added a debug define to remove functions from compilation while not needed

* ws

* convert : skip unknown tensors (need for LLaVA)

* llava : update readme

* llava : fix compile warnings

* llava : style

* convert : add --skip-unknown CLI arg

* server : remove clip structs

* bugfix for non llava-1.6

It should now work with llava-1.5 as well

* clip : minor code rearrange

* llava : update readme a bit

---------

Co-authored-by: John <cmt-nct@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-14 09:38:35 +02:00
John
6c00a06692
gguf : add python reader example (#5216)
* Update CMakeLists.txt

* Create reader.py

* Update reader.py

* Update reader.py

another whitespace :|

* Update reader.py

* lintlintlint
2024-02-13 19:56:38 +02:00
Daniel Bevenius
263978904c
finetune : rename feed-forward tensors (w1/w2/w3) (#4839)
* finetune: rename feed-forward tensors (w1/w2/w3)

This commit renames the feed-forward tensors w1, w2 and w3 to ffn_gate,
ffn_down and ffn_up respectively.

The motivation for this change is to make it easier to understand the
purpose of the tensors. This also seems to be inline with the names
used in the llama_layer struct in llama.cpp.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* train-text-from-scratch: rename ff tensors

This commit renames the feed-forward tensors w1, w2 and w3 to ffn_gate,
ffn_down and ffn_up respectively.

The motivation for this change is to make it easier to understand the
purpose of the tensors. This also seems to be inline with the names
used in the llama_layer struct in llama.cpp

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-13 15:15:42 +02:00
Douglas Hanley
03bf161eb6
llama : support batched embeddings (#5466)
* batched embedding: pool outputs by sequence id. updated embedding example

* bring back non-causal attention

* embd : minor improvements

* llama : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-13 14:06:58 +02:00
Daniel Bevenius
4a46d2b792
llava : remove prog parameter from ArgumentParser (#5457)
* llava: remove prog parameter from ArgumentParser

This commit removes the `prog` parameter from `ArgumentParser`
so that it uses the default value which is the name of the script.

The motivation for this change is that currently the usage output looks
like this:
```console
$ python examples/llava/convert-image-encoder-to-gguf.py --help
usage: convert_hf_to_gguf.py [-h] ...
```
And with this change it will look like this:
```console
$ python examples/llava/convert-image-encoder-to-gguf.py --help
usage: convert-image-encoder-to-gguf.py [-h] ...
```

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* ci: add W503 to flake8 ignore list

This commit adds W503 to the ignore list for flake8. This is done to
avoid the following error:
W503 line break before binary operator

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-12 10:38:44 +02:00
Georgi Gerganov
3b169441df
sync : ggml (#5452)
* ggml-alloc : v3 (ggml/727)

* ggml-alloc v3

ggml-ci

* fix ci

ggml-ci

* whisper : check for backend buffer allocation failures

* whisper : avoid leaks when initialization fails

* cleanup

ggml-ci

* style fixes

ggml-ci

* sync : ggml

* update llama.cpp, clip.cpp, export-lora.cpp

* update finetune.cpp, train-text-from-scratch.cpp

ggml-ci

* ggml-backend : reduce alignment to 32 to match gguf and fix mmap

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-02-12 09:16:06 +02:00
Douglas Hanley
2891c8aa9a
Add support for BERT embedding models (#5423)
* BERT model graph construction (build_bert)
* WordPiece tokenizer (llm_tokenize_wpm)
* Add flag for non-causal attention models
* Allow for models that only output embeddings
* Support conversion of BERT models to GGUF
* Based on prior work by @xyzhang626 and @skeskinen

---------

Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-11 11:21:38 -05:00
Alexey Parfenov
684780141a
server : allow to specify tokens as strings in logit_bias (#5003)
* server: allow to specify tokens as strings in logit_bias

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-11 15:38:14 +02:00
Georgi Gerganov
85910c5b30
main : ctrl+C print timing in non-interactive mode (#3873) 2024-02-11 15:35:50 +02:00
Johannes Gäßler
e4640d8fdf
lookup: add print for drafting performance (#5450) 2024-02-11 12:44:51 +01:00
Xuan Son Nguyen
907e08c110
server : add llama2 chat template (#5425)
* server: add mistral chat template

* server: fix typo

* server: rename template mistral to llama2

* server: format_llama2: remove BOS

* server: validate "--chat-template" argument

* server: clean up using_chatml variable

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2024-02-11 12:16:22 +02:00
Daniel Bevenius
e00d2a62dd
llava : add requirements.txt and update README.md (#5428)
* llava: add requirements.txt and update README.md

This commit adds a `requirements.txt` file to the `examples/llava`
directory. This file contains the required Python packages to run the
scripts in the `examples/llava` directory.

The motivation of this to make it easier for users to run the scripts in
`examples/llava`. This will avoid users from having to possibly run into
missing package issues if the packages are not installed on their system.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* llava: fix typo in llava-surgery.py output

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-09 15:00:59 +02:00
Riley Stewart
7c777fcd5d
server : fix prompt caching for repeated prompts (#5420) 2024-02-09 12:49:49 +02:00
Daniel Bevenius
ff4ff05c5f
llava : add missing .py, and fix paths in README.md (#5414)
This commit adds the missing .py extension to the convert-image-encoder-to-gguf
script. It also fixes the paths for the `model` and `mmproj` options in the
example llava-cli command.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-08 16:20:03 +02:00
Daniel Bevenius
a6e514a85f
llava: fix typo/formatting in README.md (#5405)
This commit fixes a typo in the README.md file for the llava example
which is causing the formatting to look a little off:

Clone llava-v15-7b`` and clip-vit-large-patch14-336`` locally

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-02-08 09:58:19 +01:00
Xiao-Yong Jin
0ef46da632
llava-cli : always tokenize special tokens (#5382)
* llava-cli: tokenize special tokens in prompt

* llava-cli: use the escape CLI argument, remove incomplete separate escaping process
2024-02-07 10:17:25 +02:00
Justin Parker
f3e2b4fa3f
server : update /props with "total_slots" value (#5373)
* include total "num_slots" in default_generation_settings_for_props

* cleanup total_slots return value in /props endpoint

* update /props endpoint docs with total_slots

* remove num_slots from default_generation_settings_for_props

* update /props endpoint section
2024-02-07 08:15:19 +02:00
Alexey Parfenov
213d1439fa
server : remove model.json endpoint (#5371) 2024-02-06 20:08:38 +02:00
Justin Parker
8a79c591de
server : include total "num_slots" in props endpoint (#5349) 2024-02-06 11:20:59 +02:00
Michael Coppola
31e7903221
server : add dynatemp_range and dynatemp_exponent (#5352)
* server: added `dynatemp_range` and `dynatemp_exponent`

* Update README.md

---------

Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2024-02-06 11:20:00 +02:00
Niall Coates
4ffc7a17d4
server : various fixes for the prompt field in /completion (#5300)
server : fix deadlock when prompt array contains strings and numbers

server : removed an unnecessary generation when generating multi-prompts

server : removed an unnecessary assert
2024-02-06 10:16:23 +02:00
Alexey Parfenov
a2d60c9158
server : allow to get default generation settings for completion (#5307) 2024-02-05 10:10:22 +02:00
Kawrakow
5ed26e1fc9
Adding some imatrix tools (#5302)
* imatrix: adding --combine and --continue-from

* imatrix: be able to start from a specific chunk

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-04 10:39:58 +02:00
Michael Klimenko
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291) 2024-02-03 13:23:37 +02:00
kalomaze
191221178f
perplexity : fix KL divergence calculations on Windows (#5273) 2024-02-02 16:15:30 +02:00
Neo Zhang Jianyu
af3ba5d946
[SYCL] update guide of SYCL backend (#5254)
* update guide for make installation, memory, gguf model link,  rm todo for windows build

* add vs install requirement

* update for gpu device check

* update help of llama-bench

* fix grammer issues
2024-02-02 15:53:27 +08:00
Neo Zhang Jianyu
128dcbd3c9
add --no-mmap in llama-bench (#5257)
* add --no-mmap, show sycl backend

* fix conflict

* fix code format, change print for --no-mmap

* ren no_mmap to mmap, show mmap when not default value in printer

* update guide for mmap

* mv position to reduce model reload
2024-02-01 20:48:53 +01:00
Georgi Gerganov
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
* llama : remove LLAMA_MAX_DEVICES from llama.h

ggml-ci

* Update llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* server : remove LLAMA_MAX_DEVICES

ggml-ci

* llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD

ggml-ci

* train : remove LLAMA_SUPPORTS_GPU_OFFLOAD

* readme : add deprecation notice

* readme : change deprecation notice to "remove" and fix url

* llama : remove gpu includes from llama.h

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-01-31 17:30:17 +02:00
JidongZhang-THU
15606309a0
llava : add MobileVLM support (#5132)
* New Feature:
    1. Sum_Rows:
        fix cuda kernel overflow
        fix block shape error when nrows too big
    2. Im2Col:
        Support Batch in cuda
        Support f32 to f32 both in cpu && cuda
    3. DepthWiseConv:
        Support by Im2Col && MulMat
    4. Pool_2d:
        Supoort avg pooling in cuda
    5. HardSigmoid:
        Imp in cuda
    6. HardSwish:
        Imp in cuda

* fix tabs instead of spaces

* code clean

* CUDA POOL2D

* ADD POOL2D test case in test-backend-ops.cpp

* code clean

* fix pool2d_kernel

nits

* fix bug in pool2d kernel

* fix avg pooling, count_include_pad

nits

* test-backend-ops : add more pool_2d tests

* cuda : fix warnings and formatting

* ggml : check types in release builds too in pool_2d

* test-backend-ops : remove f16 pool_2d tests

* cuda : more style fixes

* Add assert in ggml_cuda_op_pool2d

* pool2d float padding fallback

* test-backend-ops : add dst_type to im2col

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-01-31 15:10:15 +02:00
Neo Zhang Jianyu
b2b9f025e7
format license text, restore apache license by legal suggestion (#5233) 2024-01-31 18:34:46 +05:30
Neo Zhang Jianyu
01684139c3
support SYCL backend windows build (#5208)
* support SYCL backend windows build

* add windows build in CI

* add for win build CI

* correct install oneMKL

* fix install issue

* fix ci

* fix install cmd

* fix install cmd

* fix install cmd

* fix install cmd

* fix install cmd

* fix win build

* fix win build

* fix win build

* restore other CI part

* restore as base

* rm no new line

* fix no new line issue, add -j

* fix grammer issue

* allow to trigger manually, fix format issue

* fix format

* add newline

* fix format

* fix format

* fix format issuse

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-01-31 08:08:07 +05:30
Jared Van Bortel
e8dc55d006
kompute : llama-bench support and ggml_cpu_has_kompute() (#5226) 2024-01-30 19:04:37 -05:00
Georgi Gerganov
e0085fdf7c
Revert "server : change deps.sh xxd files to string literals (#5221)"
This reverts commit 4003be0e5f.
2024-01-30 21:19:26 +02:00
Georgi Gerganov
e6f291d158
server : fix context shift (#5195)
* server : fix context shift + simplify self-extend

* server : take system_tokens into account

* server : more n_past fixes

* server : rever n_past_se changes
2024-01-30 20:17:30 +02:00
JohnnyB
4003be0e5f
server : change deps.sh xxd files to string literals (#5221)
* Changed ugly xxd to literals.

HPP files are much more readable as multiline literals rather than hex arrays.

* Dashes in literal variable names.

Replace . and - with _ in file names -> variable names.

* Comment on removing xxd.

XXD-> string literals

* XXD to string literals.

Replaced these unreadable headers with string literal versions using new deps.sh.
2024-01-30 20:15:05 +02:00
Kawrakow
f4d7e54974
SOTA 3-bit quants (#5196)
* iq3_xxs: quantize/dequantize

RMSE seems a bit high-ish at about half-way between q2_K and
q3_K, so need to check more.

* iq3_xxs: CUDA dequantize works

* iq2_xxs: tuning quantization

* iq3_xxs: starting to look better

PPL on wiki.test.raw
LLaMA-v1-7B: 6.4218
LLaMA-v2-7B: 6.3560
Mistral-7B : 6.0717

This is better than Q3_K_XS, with a 5% reduction in quantized model
size.

* iq3_xxs: CUDA dot product

We have
PP-512: 5891 t/s
TG-128: 143.9 t/s

* iq3_xxs: scalar and AVX2 dot products

* iq3_xxs: ARM_NEON and Metal

Metal performance is decent, ARM_NEON is pathetic

* iq3_xxs: slightly better grid points

* Faster iq3_xxs and iq2_xs dot products on CUDA

* iq3_xxs: add some quant mix

* iq3_xxs: fix failing quantization test

Dot product still fails. Is this real?

* iq3_xxs: hopefully fix ROCm

* iq3_xxs: failing tests

This time the dot product accuracy did find an actual bug
in the AVX2 implementation.

* Add IQ3_XXS to test-backend-ops

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-30 15:14:12 +02:00
Vladimir Malyutin
7359016c7c
quantize : fix typo (#5211)
Fix misprint in quantize help
2024-01-30 12:57:07 +02:00
divinity76
813416991a
main : allow empty --prompt-cache file (#5176)
* allow empty --prompt-cache file

This allows the use of std::tmpnam(), std::tmpfile(), Python's tempfile.NamedTemporaryFile(), and similar create-empty-file API's for the user.

I switched from the C fopen API to the C++ filesystem api to get around the fact that, to the best of my knowledge, C has no portable way to get the file size above LONG_MAX, with std::ftell() returning long? fallback to std::ifstream for c++  < 17
(the project is currently targeting C++11 it seems - file_exists() and file_size() can be removed when we upgrade to c++17)

* formatting

(requested in codereview)

* remove c++17, file_is_empty
2024-01-30 11:18:02 +02:00
Wu Jian Ping
6685cc41c2
server : improve README (#5209) 2024-01-30 11:11:46 +02:00
Wu Jian Ping
c82d18e863
server : embeddings compatibility for OpenAI (#5190) 2024-01-29 15:48:10 +02:00
0cc4m
2307523d32
ggml : add Vulkan backend (#2059)
* Vulkan loader code

* Fix matmul kernel, continue implementation

* Continue implementation

* Vulkan memory management

* Vulkan development

* Matmul call

* Add aligned malloc and free for VMA

* Continue implementation

* First matmul success

* GEMM Kernel optimization

* 1D Blocktiling

* 2D Blocktiling

* Write coalescing

* Continue vulkan implementation and optimization

* First FP16 attempt, disabled for now

* Code abstraction, FP16 implementation, fix kernel, add FP16 to FP32 kernel

* Enable device extensions properly, restore fp16 matmul op

* Fix mulmat_f16

* Output FP32 in fp16 matmul shader

* Fix f16_to_f32 kernel

* dequant_q4_0 kernel

* Add VMA library

* Avoid requesting dedicated memory, VMA can decide that by itself

* Add bounds checking to matmul kernels, improve implementation, fix command buffers not freed properly

* add cmake commands

* Add 2d write operation, profiling code

* Fix 2d write

* Fix queue selection for AMD RADV

* Fix trailing whitespace in vk_mem_alloc.h

* Add WIP warp tile mat mul shaders

* Disable glslc optimization

* Disable glslc optimization for CMake

* Optimize warptile matmul shader, replace blocktile with it

* Add split-k optimization for small matrix multiplication

Use semaphores for synchronization instead of fences or waitidle

Rework async write/read for synchronization

* Fix validation errors, improve compatibility with AMD GPUs

* Rework command buffer handling

* Variable matmul kernel using specialization constants

* Fix synchronization on AMD, add barriers for buffer ownership transfer, add debug flag and prints

* Reuse semaphores

* Handle stage flags during command buffer submission properly

* Increase matmul test runs for consistent results

* Fix F32 matmul

* Add vectorized loading and zeropadding for matrix multiplication

* Use pinned memory for f16 preprocessing

* Don't force aligned matmul

* Don't free before queue done

* Replace VMA library with native Vulkan buffer management

* Basic offloading support with mul_f32 and dmmv for q4_0

* Run glslc commands in parallel

* Unroll loops in dmmv shader

* Reduce usage of waitIdle

* Reuse pinned allocation for f16 conversion

* Handle devices with only a single queue

* Fix trailing whitespace in CMakeLists.txt

* Allow parallel execution of kernels, parallelize third and fourth dimension calls

* Add fallback for devices only supporting one DescriptorSet per DescriptorPool

* Move to graph function similar to CUDA implementation

* Use F16 kernel for most things, replace q_f32 with mul_mat_q_f16 function

* Add F32 dmmv shaders

* Batch submissions

* Add .spv to gitignore

* Split off matrix vector multiplication for separate optimization

* Use single command buffer for matrix vector multiplication ops

* Reduce overhead of mul_f32 calls by using a single command buffer

* Add submission batching to mul_f32

* Fix tests

* Add missing barrier

* Add further missing barrier

* Add further ops

* Replace vk::QueueFamilyIgnored with VK_QUEUE_FAMILY_IGNORED to support more Vulkan header versions

* Remove unnecessary cblas link

* Fix descriptor set pre-allocation assert

* Add runtime shader compilation, start transferring shaders to this approach

* Transfer remaining shaders to header and compile on runtime

* Fix fp32 fallback if device doesn't support fp16, add force disable env var GGML_VULKAN_DISABLE_F16

* Add support for q4_1, q5_0, q5_1 and q8_0

* Remove unnecessary scalar layout extension

* Parse graph early to pre-record command buffers

* Add q6_k support

* Add multi-submit for command buffers

* Fix q6_k dequant shader for AMD

* Fix q6_k for GPUs without fp16 support

* Simplify q6_k fp16 fix

* Minor fixes

* Fix wg_denom of m-mulmat shaders

* Add Python-based Vulkan shader generator

* Replace shaderc dependency with precompiled shaders

Fix python script to generate shaders

* Clean up code

* Fix shader generator script Windows compatibility

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>

* Close file before deletion

* Fix vulkan shader fp32 name

* Add q2_k and q3_k support

Add validation check to compare shader results to cpu results

* Add q4_k support

* Add q5_k support

* Bake SPIR-V bytecode into the library instead of loading shaders from file

* Switch to signal semaphores for flexibility

Prepare broadcasting support for mul mat

* Finish broadcasting mul mat support for GQA

* Clean up unused functions

Add repeat op

* Add further ops, not yet enabled. Improve semaphore code

* Reduce number of used semaphores by utilizing timelines more properly

* Remove queue information

* Reuse timeline semaphores, allow parallel operation with binary semaphores to work around nvidia driver limitations

* Add Vulkan to llama-bench

* Remove cblas dependency

* Fix matmul k-split bug

* Fix q4_k dmmv K_QUANTS_PER_ITERATION 1 shader

* Add RMS Norm shader, rework op_f32 shader setup, fix matmul bug

* Fix issues with float16 overflows in shaders

* Fix issues with older Vulkan headers on Ubuntu 22.04

* Allow multi-op partial offloading by parsing the graph to preallocate enough between-op buffers

* Implement further ops, rework op_f32 calls, fix bugs

* Finish full offloading support, add last remaining ops, fix bugs, remove redundant code

* Upload generated file ggml-vulkan-shaders.hpp, remove redundant shaders

* Merge upstream changes, fix conflicts, adapt soft_max op

* Fix Python and shader header format

* Free model gpu buffers on exit

* Use single queue per device to simplify code

* Add matmul shader support for running multiple calculations in parallel

* Switch from semaphore-synchronized multiple command buffers per op to single command buffer for multiple ops, whole graph if possible

* Fix missing event cast

* Replace uint64_t(-1) with UINT64_MAX, rename function for clarity

* Fix warning about empty C function parameters

* Fix compiler warnings

* Properly implement Vulkan backend buffer handling

* Fix oversized host staging buffers

* Simplify barrier synchronization calls

* Fix gcc warnings

* Implement max_size for backend buffer types to limit the size of a single allocation

* Use min of maxMemoryAllocationSize and maxBufferSize for device max allocation size

* refactor multi buf

* Disable unsupported ops to fix tests

* Check for maintenance4 support before using it

* Handle devices with only a single queue

* Fix single queue logic

* propagate buffer usage in multi buffers

* Implement rope_neox op

* Cleanup header and other files

* Simplify gpu_extras by removing events and putting staging memcpys into contexts

* Move queue into context

Add not-yet-enabled async backend ops

* Simplify context use, optimize matmul shader for warp size 64 (AMD GCN), fix split_k matmul shader optimization

* Add get_max_size to SYCL backend.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* llama : fix trailing whitespace

---------

Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-28 19:03:59 +02:00
Abhilash Majumder
0f648573dd
ggml : add unified SYCL backend for Intel GPUs (#2690)
* first update for migration

* update init_cublas

* add debug functio, commit all help code

* step 1

* step 2

* step3 add fp16, slower 31->28

* add GGML_LIST_DEVICE function

* step 5 format device and print

* step6, enhance error check, remove CUDA macro, enhance device id to fix none-zero id issue

* support main device is non-zero

* step7 add debug for code path, rm log

* step 8, rename all macro & func from cuda by sycl

* fix error of select non-zero device, format device list

* ren ggml-sycl.hpp -> ggml-sycl.h

* clear CMAKE to rm unused lib and options

* correct queue: rm dtct:get_queue

* add print tensor function to debug

* fix error: wrong result in 658746bb26702e50f2c59c0e4ada8e9da6010481

* summary dpct definition in one header file to replace folder:dpct

* refactor device log

* mv dpct definition from folder dpct to ggml-sycl.h

* update readme, refactor build script

* fix build with sycl

* set nthread=1 when sycl, increase performance

* add run script, comment debug code

* add ls-sycl-device tool

* add ls-sycl-device, rm unused files

* rm rear space

* dos2unix

* Update README_sycl.md

* fix return type

* remove sycl version from include path

* restore rm code to fix hang issue

* add syc and link for sycl readme

* rm original sycl code before refactor

* fix code err

* add know issue for pvc hang issue

* enable SYCL_F16 support

* align pr4766

* check for sycl blas, better performance

* cleanup 1

* remove extra endif

* add build&run script, clean CMakefile, update guide by review comments

* rename macro to intel hardware

* editor config format

* format fixes

* format fixes

* editor format fix

* Remove unused headers

* skip build sycl tool for other code path

* replace tab by space

* fix blas matmul function

* fix mac build

* restore hip dependency

* fix conflict

* ren as review comments

* mv internal function to .cpp file

* export funciton print_sycl_devices(), mv class dpct definition to source file

* update CI/action for sycl code, fix CI error of repeat/dup

* fix action ID format issue

* rm unused strategy

* enable llama_f16 in ci

* fix conflict

* fix build break on MacOS, due to CI of MacOS depend on external ggml, instead of internal ggml

* fix ci cases for unsupported data type

* revert unrelated changed in cuda cmake
remove useless nommq
fix typo of GGML_USE_CLBLAS_SYCL

* revert hip cmake changes

* fix indent

* add prefix in func name

* revert no mmq

* rm cpu blas duplicate

* fix no_new_line

* fix src1->type==F16 bug.

* pass batch offset for F16 src1

* fix batch error

* fix wrong code

* revert sycl checking in test-sampling

* pass void as arguments of ggml_backend_sycl_print_sycl_devices

* remove extra blank line in test-sampling

* revert setting n_threads in sycl

* implement std::isinf for icpx with fast math.

* Update ci/run.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/sycl/run-llama2.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/sycl/run-llama2.sh

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update CMakeLists.txt

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* add copyright and MIT license declare

* update the cmd example

---------

Co-authored-by: jianyuzh <jianyu.zhang@intel.com>
Co-authored-by: luoyu-intel <yu.luo@intel.com>
Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-28 17:56:23 +02:00
Kyle Mistele
39baaf55a1
docker : add server-first container images (#5157)
* feat: add Dockerfiles for each platform that user ./server instead of ./main

* feat: update .github/workflows/docker.yml to build server-first docker containers

* doc: add information about running the server with Docker to README.md

* doc: add information about running with docker to the server README

* doc: update n-gpu-layers to show correct GPU usage

* fix(doc): update container tag from `server` to `server-cuda` for README example on running server container with CUDA
2024-01-28 09:55:31 +02:00
John
6db2b41a76
llava : support for Yi-VL and fix for mobileVLM (#5093)
* Support for Yi-VL, templating fix for mobileVLM

* ws

* Update examples/llava/clip.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update llava-cli.cpp

* Update clip.cpp

bugfix for new conversions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-27 17:09:18 +02:00
Georgi Gerganov
753eafed0e
sync : ggml 2024-01-27 17:00:24 +02:00
Michael Klimenko
35a2ee9143
Remove unused data and add fixes (#5154)
* Remove unused data and add fixes

* Add missing file

* Address review comments

* Replace the scope of vq allocation
2024-01-27 15:25:55 +01:00
Maximilian Winter
ec903c0341
server : add self-extend support (#5104)
* Ported self extension to server example

* Update server.cpp

* Fixed prompt caching without self extend

* Update server.cpp

* Added description to server readme.

* Update server.cpp

* Update server.cpp

* Update server.cpp

* Update server.cpp

* Update README.md

* Changed descriptions

* server : formatting

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update server.cpp

* Update server.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-27 15:38:05 +02:00
Xuan Son Nguyen
48c857aa10
server : refactored the task processing logic (#5065)
* server: add llama_server_queue struct

* server: add llama_server_response_event

* server: add comments

* server: move all mutexes away from server.cpp

* server: correct multitask response

* server: only add back deferred tasks when one slot is available

* server: fix a race condition cause by "request_completion"
2024-01-26 14:42:20 +02:00
Jared Van Bortel
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099) 2024-01-25 14:51:24 -05:00
Valentin Konovalov
256d1bb0dd
android : use release cmake build type by default (#5123) 2024-01-25 19:05:51 +02:00
Kawrakow
44879ee885
Additional KL-divergence statistics (#5081)
* perplexity: add top-token probability

* perplexity: add additional KL-divergence statistics

* perplexity: a better organized KL-divergence statistics output

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-23 15:17:20 +02:00
Georgi Gerganov
89758723c7
minor : clean-up some warnings and style (#5094)
* minor : clean-up some warnings and style

ggml-ci

* ggml : add comment
2024-01-23 14:12:57 +02:00
Michael Coppola
125d03a503
llama.vim : added api key support (#5090)
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2024-01-23 08:51:27 +02:00
Kawrakow
6f9939d119
KL-divergence (#5076)
* kl-divergence: be able to save all logits to a file

* Add ability to compute KL-divergence

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-22 16:10:14 +02:00
XiaotaoChen
3ce7e8f8e7
llava : MobileVLM support (#4954)
* MobileVLM native implementation

* delete depthwise_conv_2d and permute_cpy relative code, replace the two by the existed functions, and opt ldp definition, support LLAMA_PERF option for CMake

* move android script to example/llava directory

* Fix the editor config checks

---------

Co-authored-by: Chenxiaotao03 <chenxiaotao03@meituan.com>
2024-01-22 15:09:35 +02:00
Kawrakow
15bceec2d7
imatrix : keep intermediate imatrix results (#5077)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-22 14:18:43 +02:00
Daniel Bevenius
152d9d05e0
finetune : print sample-start/include-sample-start (#5072)
This commit adds `--sample-start` and `--include-sample-start` to the
output from the main function in finetune.cpp.

The motivation for this is that even though these are set explicitly by
the user via the command line, if one forgets to set them then it is
useful to have their values printed out. Otherwise it is possible to go
through the whole training process before realizing that the values are
not what one expected.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-22 13:11:01 +02:00
Kawrakow
66d575c45c
llama : add Q3_K_XS (#5060)
* Add Q3_K_XS - intermediate size between Q2_K and Q3_K_S

* Q3_K_XS: quanize first 1/8 of ffn_down layers with Q4_K

Together with an importance matrix, this brings perplexity
for LLaMA-v2-70B below the perplexity of the former Q2_K
with a 800 MB smaller quantized model size.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-22 12:43:33 +02:00
Kawrakow
7dcbe39d36
Add ability to evauate multiple choice tasks (#5047)
* TruthfulQA: 1st attempt, does not look like it is working

The same implementation can be used for HellaSwag as well,
so I converted a HellaSwag validation dataset to the binary
format used here and tested with that. The score is only
around 50, so something is not quite right.

* TruthfulQA: works but the result is bad

I know it works because if I convert the HellaSwag validation
data to the binary format used in the truthful_qa_score() function
I get the exact same result as from the hellaswag_score() function.
But I guess, the questions are tricky and the way I have done
the combination of question + answer is very likely not the best.
The TruthfulQA validation dataset contains 817 questions, with
random chance result around 19%. With this version I get
29.1% for Mistral-7B and 55.2% for Mistral-7B-Instruct-v0.2.
The HF leader board results for these two models are
42.2% and 68.3%, respectively.

* TruthfulQA: fix random sample

* TruthfulQA: prepare tasks in parallel for large test datasets

* Rename truthful_qa to multiple_choice

* Make MSVC happy

I had forgotten that MSVC does not make constexpr's available
inside a lambda.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-21 14:42:44 +02:00
Kawrakow
726c0fa9a2
Slightly faster imatrix (#5050)
* imatrix: speedup by avoiding unnecessary allocations and copies

* imatrix: add --no-ppl option to skip PPL calculations altogether

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-21 08:01:20 +02:00
Jared Van Bortel
97c1549808
perplexity : fix MSVC build after #5020 (#5043)
* perplexity : fix MSVC build after #5020

* try a differerent fix
2024-01-20 17:08:08 +02:00
Uzo Nweke
381ee19572
finetune : fix ggml_allocr lifetimes (tmp workaround) (#5033)
* Fix issue with alloc causing max_compute_size to be calculated

* remove ggml_allocr_free as suggested in issue #4791
2024-01-19 20:20:50 +02:00
Georgi Gerganov
a5cacb22b2
imatrix : add README.md 2024-01-19 15:24:47 +02:00
Kawrakow
7051aacfac
winogrande: evaluate log-probs in parallel (#5036)
This is a relatively minor performance tweak resulting in
~10% speedup on my system.

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-19 11:39:11 +02:00
Kawrakow
993fba8180
perplexity: avoid unnecessary alloocations and logit copies (#5035)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-19 11:02:39 +02:00
Georgi Gerganov
8b20858e5e
perplexity : faster Winogrande via batching (#5024)
* perplexity : faster Winogrande via batching

ggml-ci

* perplexity : remove unused function

* perplexity : only tokenize selected tasks for Winogrande
2024-01-19 10:45:06 +02:00
Xuan Son Nguyen
821f0a271e
server : defer tasks when "slot unavailable" (#5018)
* server: defer task when no slot is available

* remove unnecessary log

---------

Co-authored-by: Xuan Son Nguyen <xuanson.nguyen@snowpack.eu>
2024-01-18 22:33:05 +02:00
Georgi Gerganov
2d5419d08a
imatrix : fix assert for src0 non-cont check 2024-01-18 21:45:51 +02:00
Georgi Gerganov
d391ae9b49
perplexity : fix winogrande N tasks option 2024-01-18 20:49:00 +02:00
Kawrakow
3e945cc1e9
HellaSwag: speed up by parallelizing log-prob evaluation (#5020)
For Mistral-7B and fp16, time on my system goes down from 536 seconds
to 423 seconds for the full evaluation dataset (10042 tasks).

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-18 19:18:21 +02:00
Georgi Gerganov
ad19812cda
perplexity : faster HellaSwag via batching (#5017)
* perplexity : faster HellaSwag

ggml-ci

* perplexity : clean-up

ggml-ci

* perplexity : no need for decode_helper

ggml-ci

* perplexity : add comments

* perplexity : option to specify max batched tasks via `n_parallel`

* perplexity : remove HellaSwag restruction for n_batch
2024-01-18 15:33:01 +02:00
Kawrakow
682986a08e
Add Winogrande evaluation (#5015)
* winogrande: simple implementation

It doesn't look like it is working - why?
For Mistral-7B it is barely better than
random chance (score ~60% for 1267 tasks), while I see
Mistral-7B scoring 78.4% on the HF leader board.
1-sigma statistical uncertainty for 1267 tasks is ~1.4,
so no way the difference is due to statistics.

* winogrande: somewhat better

Score for Mistrali7-B is now 68.9 on the validation set of
winogrande_debiased. Still far from the reported 78.4, but
better than what I had before.

* winogrande: improving

Mistral-7B score is now 73.56.
Still not quite 78.4 but getting there.
We are also getting a lower score on HellaSwag
compared to HF leader board, so I'm not expecting
we will get up to 78.4 anyway.

It looks like it is better to skip the choice word(s)
when evaluating the average log-likelihood. This kind of
makes sense because a more common word (in Winogrande this is
often a name) will have a higher probability without knowing
about the follow up context, and this will skew the log-likelihood
towards the more common word. We can only do this if the
choice words are not last in the sentence.

It also looks like it is better to skip the punctuation at the
end of the sentence, provided the choice words are not last.

* winogrande: add dataset instructions

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-18 13:46:27 +02:00
Georgi Gerganov
ba69bbc84c
imatrix : offload to GPU support (#4957)
* backend : add eval callback

ggml-ci

* backend : group nodes in a single compute when user don't need them

* backend : clean-up the implementation

ggml-ci

* simple : do not perform tensor data copy if not needed

* simple : fix

* imatrix : offload to GPU support

* imatrix : fix ggml_mul_mat_id hanlding

ggml-ci

* ci : add imatrix test

ggml-ci

* ci : rearrange output

ggml-ci
2024-01-17 18:46:30 +02:00
Daniel Bevenius
cec8a48470
finetune : add training data file to log message (#4979)
This commit adds the name of the training data file to the log message
printed when the training data is tokenized.

The motivation for this change is that it can be useful to show which
file is being tokenized when running the finetune example.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-16 19:54:24 +02:00
Maximilian Winter
4feb4b33ee
examples : add complete parallel function calling example (#4974) 2024-01-16 19:41:42 +02:00
Georgi Gerganov
959ef0c0df
perplexity : fix kv cache handling for hellaswag (#4981)
ggml-ci
2024-01-16 19:34:54 +02:00
Neuman Vong
862f5e41ab
android : introduce starter project example (#4926)
* Introduce starter project for Android

Based on examples/llama.swiftui.

* Add github workflow

* Set NDK version

* Only build arm64-v8a in CI

* Sync bench code

* Rename CI prop to skip-armeabi-v7a

* Remove unused tests
2024-01-16 15:47:34 +02:00
Maximilian Winter
122ed4840c
examples : fix and improv docs for the grammar generator (#4909)
* Create pydantic-models-to-grammar.py

* Added some comments for usage

* Refactored Grammar Generator

Added example and usage instruction.

* Update pydantic_models_to_grammar.py

* Update pydantic-models-to-grammar-examples.py

* Renamed module and imported it.

* Update pydantic-models-to-grammar.py

* Renamed file and fixed grammar generator issue.

* Fixed some issues and bugs of the grammar generator. Imporved Documentation

* Update pydantic_models_to_grammar.py
2024-01-16 14:10:48 +02:00
Daniel Bevenius
d75c232e1d
finetune : use LLAMA_FILE_MAGIC_GGLA (#4961)
This commit replaces the magic number LLAMA_FILE_MAGIC_LORA used in
finetune.cpp with LLAMA_FILE_MAGIC_GGLA defined in llama.h.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-16 13:14:19 +02:00
stduhpf
e0324285a5
speculative : threading options (#4959)
* speculative: expose draft threading

* fix usage format

* accept -td and -tbd args

* speculative: revert default behavior when -td is unspecified

* fix trailing whitespace
2024-01-16 13:04:32 +02:00
Kawrakow
467a882fd2
Add ability to use importance matrix for all k-quants (#4930)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-14 16:21:12 +02:00
Kawrakow
147b17ac94
2-bit quantizations (#4897)
* imatrix: load

* imatrix: WIP

* imatrix: Add Q2_K quantization

* imatrix: also guard against Q2_K_S quantization without importance matrix

* imatrix: guard even more against low-bit quantization misuse

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-14 09:45:56 +02:00
Georgi Gerganov
4be5ef556d
metal : remove old API (#4919)
ggml-ci
2024-01-13 20:45:45 +02:00
Georgi Gerganov
0ea069b87b
server : fix prompt caching with system prompt (#4914) 2024-01-13 19:31:26 +02:00
David Friehs
df845cc982
llama : minimize size used for state save/load (#4820)
* examples : save-load-state: save only required state

* llama : only reserve n_vocab * n_batch at most for logits

llama_decode asserts that only n_batch tokens are passed each call, and
n_ctx is expected to be bigger than n_batch.

* llama : always reserve n_vocab * n_batch for logits

llama_context de-serialization breaks if the contexts have differing
capacity for logits and llama_decode will at maximum resize to
n_vocab * n_batch.

* llama : only save and restore used logits

for batch sizes of 512 this reduces save state in the best case by
around 62 MB, which can be a lot if planning to save on each message
to allow regenerating messages.

* llama : use ostringstream and istringstream for save and load

* llama : serialize rng into minimum amount of space required

* llama : break session version due to serialization changes
2024-01-13 18:29:43 +02:00
Yann Follet
722d33f34e
main : add parameter --no-display-prompt (#4541)
* add the parameter : --no-display-prompt , combine with --log-disable it will display only the generated tokens

* remove empty line

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-13 18:09:08 +02:00
Ziad Ben Hadj-Alouane
356327feb3
server : fix deadlock that occurs in multi-prompt scenarios (#4905)
* * fix deadlock

* * dont ruint all whitespace
2024-01-13 16:20:46 +02:00
makomk
ee8243adaa
server : fix crash with multimodal models without BOS token (#4904) 2024-01-13 16:16:11 +02:00
Maximilian Winter
52ee4540c0
examples : add pydantic models to GBNF grammar generator (#4883)
* Create pydantic-models-to-grammar.py

* Added some comments for usage

* Refactored Grammar Generator

Added example and usage instruction.

* Update pydantic_models_to_grammar.py

* Update pydantic-models-to-grammar-examples.py

* Renamed module and imported it.

* Update pydantic-models-to-grammar.py

* Renamed file and fixed grammar generator issue.
2024-01-12 21:46:45 +02:00
slaren
e7e4df031b
llama : ggml-backend integration (#4766)
* llama : ggml-backend integration

* ggml-backend : add names to buffers

* fix unmap after loading

* batched-bench : add tensor_split param

* llama : check for null tensor_split

* ggml-backend : increase GGML_MAX_BACKENDS

* improve graph splitting, partial fix for --no-kv-offload

* cuda : add ggml-backend split buffer support

* cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available)

* ggml : fix null backend dereference (#4807)

* ggml : fix null backend dereference

* ggml : also check ggml_backend_is_cpu

* test-backend-ops : check buffer allocation failures

* llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row)

* ggml : fix mul_mat_id work size

* llama : rewrite session kv load/set without graphs

* minor

* llama : only initialize used backends, free backends on context free

* llama : abort ctx if cuda backend init fails

* llama : rewrite lora with ggml-backend and compute on CPU

ggml-ci

* llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer

* opencl : add ggml-backend buffer type

* cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf)

* llama : on Metal, by default offload the full model

ggml-ci

* metal : page align the data ptr (#4854)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix split buffer free

* address review comments

* llama-bench : add split-mode parameter

* fix whitespace

* opencl : fix double initialization

* server : add --split-mode parameter

* use async copy and compute to improve multi-gpu performance

ggml-ci

* use async memcpys to copy the graph outputs to the CPU

* fix opencl

* use a host buffer for the cpu compute buffer for faster copies to the gpu

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2024-01-12 20:07:38 +01:00
Daniel Bevenius
930f907d3e
export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894)
This commit replaces the magic number used in export-lora.cpp with
the one defined in llama.h, which is indirectly included via common.h.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-12 19:54:53 +02:00
Zay
e790eef21c
llama.swiftui : update models layout (#4826)
* Updated Models Layout

- Added a models drawer
- Added downloading directly from Hugging Face
- Load custom models from local folder
- Delete models by swiping left

* trimmed trailing white space

* Updated Models Layout
2024-01-12 14:48:00 +02:00
Kawrakow
326b418b59
Importance Matrix calculation (#4861)
* imatrix: 1st version

* imatrix: WIP

* Cleanup

* Update examples/imatrix/imatrix.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-12 06:59:57 +01:00
Georgi Gerganov
1d118386fe
server : fix infill when prompt is empty (#4833) 2024-01-11 23:23:49 +02:00
Georgi Gerganov
7edefbd79c
main : better name for variable n_print (#4874) 2024-01-11 22:46:26 +02:00
Georgi Gerganov
3ca63b4538
main : disable token count by default (#4874) 2024-01-11 22:43:05 +02:00
Kawrakow
469e75d0a3
llama : restore intended k-quants mixes for MoE models (#4872)
* Restore intended k-quants quantization mixes for MoE models

* Update Q2_K_S values in the quantize tool

Still using LLaMA-v1 PPL values in the quant description
today does not make much sense. But let's leave this update
for another PR.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-11 21:43:15 +02:00
Laura
4330bd83fe
server : implement credentialed CORS (#4514)
* Implement credentialed CORS according to MDN

* Fix syntax error

* Move validate_api_key up so it is defined before its first usage
2024-01-11 20:02:48 +02:00
Michael Coppola
27379455c3
server : support for multiple api keys (#4864)
* server: added support for multiple api keys, added loading api keys from file

* minor: fix whitespace

* added file error handling to --api-key-file, changed code to better
reflect current style

* server: update README.md for --api-key-file

---------

Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2024-01-11 19:51:17 +02:00
Behnam M
eab6795006
server : add LOG_INFO when model is successfully loaded (#4881)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line

* updated `server` readme to document the `/health` endpoint too

* used LOG_INFO after successful model loading
2024-01-11 19:41:39 +02:00
pudepiedj
43f76bf1c3
main : print total token count and tokens consumed so far (#4874)
* Token count changes

* Add show token count

* Updating before PR

* Two requested changes

* Move param def posn
2024-01-11 18:14:52 +02:00
Isaac McFadyen
2f043328e3
server : fix typo in model name (#4876) 2024-01-11 16:33:26 +02:00
Behnam M
7a9f75c38b
server : update readme to document the new /health endpoint (#4866)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line

* updated `server` readme to document the `/health` endpoint too
2024-01-11 09:12:05 +02:00
Georgi Gerganov
5c1980d8d4
server : fix build + rename enums (#4870) 2024-01-11 09:10:34 +02:00
Behnam M
cd108e641d
server : add a /health endpoint (#4860)
* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line
2024-01-10 21:56:05 +02:00
John
d34633d8db
clip : support more quantization types (#4846)
Uses ggml functions instead of hardcoded names and adds support to quantize into the modern Q-K variants.
This is just the bare minimum to get k-types working - a more refined choice of types would be needed to get best quality on low quantizations.

I ran a few tests, it doesn't break anything I could notice and a Q6_K ViT works almost as well as Q8_0 but 3 times the inference speed.
2024-01-10 15:37:09 +02:00
Justine Tunney
36e5a08b20
llava-cli : don't crash if --image flag is invalid (#4835)
This change fixes an issue where supplying `--image missing-file` would
result in a segfault due to a null pointer being dereferenced. This can
result in distracting info being printed if robust crash analysis tools
are being used.
2024-01-09 19:59:14 +02:00
Behnam M
128de3585b
server : update readme about token probs (#4777)
* updated server readme to reflect the gg/server-token-probs-4088 commit

added explanation for the API's completion result which now includes `completion_probabilities`. Also added a JSON schema that shows the type/structure of `completion_probabilities`.

* simplified the `completion_probabilities` JSON schema 

It's now easier to understand what the structure of `completion_probabilities` looks like.

* minor : fix trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-09 12:02:05 +02:00
Zsapi
8c58330318
server : add api-key flag to documentation (#4832)
Document the api-key flag added to server in https://github.com/ggerganov/llama.cpp/pull/4441
2024-01-09 11:12:43 +02:00
Georgi Gerganov
42ea63c5a3
llama.swiftui : update readme 2024-01-08 15:57:36 +02:00
Georgi Gerganov
52531fdff8
main : add self-extend support (#4815)
* examples : add passkey test

* passkey : better prints

* passkey : select pass key pos from CLI

* passkey : simplify n_past logic

* llama : "self-extend"-like context extension

* passkey : add comment

* main : add Self-Extend support

* llama : add comment about llama_kv_cache_seq_div
2024-01-08 11:18:32 +02:00
Georgi Gerganov
b0034d93ce
examples : add passkey test (#3856)
* examples : add passkey test

* passkey : better prints

* passkey : select pass key pos from CLI

* passkey : simplify n_past logic

* make : add passkey target

* passkey : add "self-extend"-like context extension (#4810)

* llama : "self-extend"-like context extension

* passkey : add comment

* passkey : add readme
2024-01-08 11:14:04 +02:00
slaren
226460cc0d
llama-bench : add no-kv-offload parameter (#4812) 2024-01-07 17:59:01 +01:00
Alex Azarov
72d8407b36
llama.swiftui : use llama.cpp as SPM package (#4804) 2024-01-07 10:20:50 +02:00
Alex Azarov
3418c03ecc
llama.swiftui : add visionOS target (#4805) 2024-01-07 09:46:55 +02:00
Georgi Gerganov
67984921a7
server : fix n_predict check (#4798) 2024-01-07 08:45:26 +02:00
Daniel Illescas Romero
c75ca5d96f
llama.swiftui : use correct pointer for llama_token_eos (#4797) 2024-01-06 17:12:59 +02:00
Georgi Gerganov
96e80dabc6
examples : improve base-translate.sh script (#4783) 2024-01-06 11:40:24 +02:00
Georgi Gerganov
91d38876df metal : switch back to default.metallib (ggml/681)
ggml-ci
2024-01-05 18:02:06 +02:00
Georgi Gerganov
3681f22443
examples : add few-shot translation example (#4783) 2024-01-05 15:11:10 +02:00
Daniel Bevenius
b3a7c20b5c
finetune : remove unused includes (#4756)
This commit removes unused includes from finetune.cpp.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-04 21:45:37 +02:00
Georgi Gerganov
012cf349ae
server : send token probs for "stream == false" (#4714) 2024-01-04 19:56:33 +02:00
singularity
3c0b585561
llama.swiftui : support loading custom model from file picker (#4767)
* swiftui: support load model from file picker

* swiftui: remove trailing whitespace
2024-01-04 10:22:38 +02:00
Michael Coppola
e5804313a1
server : fix options in README.md (#4765)
* fix examples/server/README.md

* minor : fix whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-04 10:17:09 +02:00
singularity
46cea79e1f
llama.swiftui : fix build of ggml.metallib (#4754)
* metal: fix metal backend init failure in swiftui

* metal: build ggml.metallib instead of copy src

* llama.swift : remove debug flags from metallib build

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-04 09:58:16 +02:00
Justin Parker
f2eb19bd8b
server : throw an error when slot unavailable (#4741) 2024-01-03 10:43:19 +02:00
Phil H
0ef3ca2ac6
server : add token counts to html footer (#4738)
* server: add token counts to stats

* server: generate hpp

---------

Co-authored-by: phiharri <ph@got-root.co.uk>
2024-01-02 17:48:49 +02:00
Georgi Gerganov
32866c5edd
editorconfig : fix whitespace and indentation #4710 2024-01-02 13:28:15 +02:00
minarchist
5d7002d437
server : add --override-kv parameter (#4710)
* Changes to server to allow metadata override

* documentation

* flake.nix: expose full scope in legacyPackages

* flake.nix: rocm not yet supported on aarch64, so hide the output

* flake.nix: expose checks

* workflows: nix-ci: init; build flake outputs

* workflows: nix-ci: add a job for eval

* workflows: weekly `nix flake update`

* workflows: nix-flakestry: drop tag filters

...and add a job for flakehub.com

* workflows: nix-ci: add a qemu job for jetsons

* flake.nix: suggest the binary caches

* flake.lock: update

to a commit recently cached by nixpkgs-cuda-ci

---------

Co-authored-by: John <john@jLap.lan>
Co-authored-by: Someone Serge <sergei.kozlukov@aalto.fi>
2024-01-02 12:38:15 +02:00
Daniel Bevenius
775ac8712a
finetune: fix typo in README.md (#4733)
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-02 10:16:55 +01:00
Georgi Gerganov
9fbda719de
clip : refactor + bug fixes (#4696)
* clip : refactor + bug fixes

ggml-ci

* server : add log message
2023-12-30 23:24:42 +02:00
Georgi Gerganov
0235b9b571
clip : use ggml_backend_buffer_is_host (#4205) 2023-12-29 18:53:34 +02:00
Steward Garcia
ce18d727a4
clip : enable gpu backend (#4205)
* clip: enable CUDA backend

* add missing kernels

* add enough padding for alignment

* remove ggml_repeat of clip.cpp

* add metal backend

* llava : fixes

- avoid ggml_repeat
- use GGML_USE_ instead of CLIP_USE_ macros
- remove unused vars

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-29 18:52:15 +02:00
Cuong Trinh Manh
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
* fix "ld: warning: ignoring duplicate libraries: '../libllama.a'"

* fix warning in example.
2023-12-29 16:39:15 +02:00
Justine Tunney
4af4801566
llava-cli : refactor to use sampling library (#4669)
This change makes it possible to use flags like `--grammar` when using
the `llava-cli` program. The rest is just code cleanup deleting a long
standing TODO comment.

This change also ensures that logging information is emitted to stderr
which helps the `llava-cli` command be more friendly to shell scripts.

See Mozilla-Ocho/llamafile@1cd334f
2023-12-29 16:38:38 +02:00
Justine Tunney
db49ff8ed7
server : replace sleep with condition variables (#4673)
The server currently schedules tasks using a sleep(5ms) busy loop. This
adds unnecessary latency since most sleep implementations do a round up
to the system scheduling quantum (usually 10ms). Other libc sleep impls
spin for smaller time intervals which results in the server's busy loop
consuming all available cpu. Having the explicit notify() / wait() code
also helps aid in the readability of the server code.

See mozilla-Ocho/llamafile@711344b
2023-12-29 16:24:12 +02:00
SakuraUmi
60f55e888c
server : fix OpenAI server sampling w.r.t. penalty. (#4675) 2023-12-29 16:22:44 +02:00
Karthik Sethuraman
b93edd22f5
server : allow to generate multimodal embeddings (#4681) 2023-12-29 16:22:10 +02:00
andrijdavid
82d6eab224
main-cmake-pkg : fix build issue (#4665)
* Fix main-cmake-pkg compilation

* Use glob to load common files

* cmake : fix trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-29 16:18:20 +02:00
Peter Sugihara
afd997ab60
llama.swiftui : fix infinite loop, ouput timings, buff UI (#4674)
* fix infinite loop

* slight UI simplification, clearer UX

* clearer UI text, add timings to completion log
2023-12-29 15:58:56 +02:00
Justine Tunney
65e5f6dadb
Fix OpenAI server sampling w.r.t. temp and seed (#4668)
The default values for tfs_z and typical_p were being set to zero, which
caused the token candidates array to get shrunk down to one element thus
preventing any sampling. Note this only applies to OpenAI API compatible
HTTP server requests.

The solution is to use the default values that OpenAI documents, as well
as ensuring we use the llama.cpp defaults for the rest. I've tested this
change still ensures deterministic output by default. If a "temperature"
greater than 0 is explicitly passed, then output is unique each time. If
"seed" is specified in addition to "temperature" then the output becomes
deterministic once more.

See mozilla-Ocho/llamafile#117
See mozilla-Ocho/llamafile@9e4bf29
2023-12-28 15:20:00 -04:00
Daniel Bevenius
879b690a9e
finetune : fix output formatting in print_params (#4653)
This commit fixes the output formatting in the print_params function
which currently looks like this:
```console
print_params: n_vocab:   32000
print_params: n_ctx:     128
print_params: n_embd:    4096
print_params: n_ff:      11008
print_params: n_head:    32
print_params: n_head_kv: 32
print_params: n_layer:   32
print_params: norm_rms_eps          : 0.000010
print_params: rope_freq_base        : 10000.000000
print_params: rope_freq_scale       : 1.000000
```
With this comit the output will look like this:
```console
print_params: n_vocab               : 32000
print_params: n_ctx                 : 128
print_params: n_embd                : 4096
print_params: n_ff                  : 11008
print_params: n_head                : 32
print_params: n_head_kv             : 32
print_params: n_layer               : 32
print_params: norm_rms_eps          : 0.000010
print_params: rope_freq_base        : 10000.000000
print_params: rope_freq_scale       : 1.000000
```

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2023-12-27 16:16:55 +02:00
Alexey Parfenov
6123979952
server : allow to specify custom prompt for penalty calculation (#3727) 2023-12-23 11:31:49 +02:00
LeonEricsson
7082d24cec
lookup : add prompt lookup decoding example (#4484)
* initial commit, going through initializations

* main loop finished, starting to debug

* BUG: generates gibberish/repeating tokens after a while

* kv_cache management

* Added colors to distinguish drafted tokens (--color). Updated README

* lookup : fix token positions in the draft batch

* lookup : use n_draft from CLI params

* lookup : final touches

---------

Co-authored-by: Leon Ericsson <leon.ericsson@icloud.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-22 18:05:56 +02:00
Georgi Gerganov
afefa319f1
ggml : change ggml_scale to take a float instead of tensor (#4573)
* ggml : change ggml_scale to take a float instead of tensor

* ggml : fix CPU implementation

* tests : fix test-grad0

ggml-ci
2023-12-21 23:20:49 +02:00
Georgi Gerganov
32259b2dad
gguf : simplify example dependencies 2023-12-21 23:08:14 +02:00
Georgi Gerganov
0e18b2e7d0
llama.swiftui : add tinyllama 1.1B F16 2023-12-18 20:17:43 +02:00
Georgi Gerganov
6ff39b129d
llama.swiftui : add more models 2023-12-18 20:05:12 +02:00
Georgi Gerganov
800a489e4a
llama.swiftui : add bench functionality (#4483)
* llama.swiftui : add bench button

* llama.swiftui : initial bench functionality

* force to use n_gpu_layers on simulator

* add download buttons & expose llamaState.loadModel

* update project.pbxproj

* comment #Preview & fix editorconfig check

* gitignore : xcode stuff

* llama.swiftui : UX improvements

* llama.swiftui : avoid data copy via "downloadTask"

* llama.swiftui : remove model from project

* llama : remove "mostly" from model infos

* llama.swiftui : improve bench

---------

Co-authored-by: jhen <developer@jhen.me>
2023-12-17 19:38:41 +02:00
slaren
45668633fd
finetune : keep allocs alive until all allocations are done (#4486) 2023-12-17 16:05:56 +01:00
olexiyb
0ffc92d2d2
server : disable llm logs if SERVER_VERBOSE is off (#3792) 2023-12-17 17:02:16 +02:00
AdithyanI
8edd2b40fd
server : fix grammar being ignored (#4494)
Fix bug in identifying the grammar.
2023-12-17 16:57:56 +02:00
Alexey Parfenov
eb16dae7e7
server : fix possible ambiguity in content type charset (#4501) 2023-12-17 16:56:09 +02:00
mzcu
62bd52b7bf
server : allow requests larger than 8K (#4500) 2023-12-17 16:54:37 +02:00
ShadovvBeast
88ae8952b6
server : add optional API Key Authentication example (#4441)
* Add API key authentication for enhanced server-client security

* server : to snake_case

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-15 13:49:01 +02:00
slaren
cafcd4f895
ggml : remove n_dims from ggml_tensor (#4469)
ggml-ci
2023-12-14 16:52:08 +01:00
LostRuins
20a68a7030
ggml : add ggml_row_size() (fixes llama out of space) (#4461)
* Fixes "Not enough space in the context's memory pool" encountered on certain models, which seems to be caused by some imprecision related to the automatic casting of floating point values

* do not cast to size_t, instead just use doubles

* ggml : add ggml_row_size(), deprecate ggml_type_sizef()

* ggml : fix row size compute to avoid overflows

* tests : fix sizey -> sizez

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-14 14:13:33 +02:00
shibe2
948ff137ec
server : fix handling of characters that span multiple tokens when streaming (#4446) 2023-12-13 21:57:15 +02:00
kalomaze
fecac45658
server : tweak default sampling parameters (#4367)
* Set a more typical Top P setting as the default

* Update temp max
2023-12-12 12:12:35 +02:00
Richard Kiss
9494d7c477
english : use typos to fix comments and logs (#4354) 2023-12-12 11:53:36 +02:00
Vladimir Zorin
d9d4cfef64
server : fix local model name in server (#4420) 2023-12-12 11:25:29 +02:00
Yueh-Po Peng
8a7b2fa528
Update README.md (#4388)
Fix small typo.
2023-12-10 23:27:38 +01:00
Georgi Gerganov
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
* per-layer KV

* remove unnecessary copies

* less code duplication, offload k and v separately

* llama : offload KV cache per-layer

* llama : offload K shift tensors

* llama : offload for rest of the model arches

* llama : enable offload debug temporarily

* llama : keep the KV related layers on the device

* llama : remove mirrors, perform Device -> Host when partial offload

* common : add command-line arg to disable KV cache offloading

* llama : update session save/load

* llama : support quantum K cache (#4312)

* llama : support quantum K cache (wip)

* metal : add F32 -> Q8_0 copy kernel

* cuda : add F32 -> Q8_0 copy kernel

ggml-ci

* cuda : use mmv kernel for quantum cache ops

* llama : pass KV cache type through API

* llama : fix build

ggml-ci

* metal : add F32 -> Q4_0 copy kernel

* metal : add F32 -> Q4_1 copy kernel

* cuda : wip

* cuda : add F32 -> Q4_0 and F32 -> Q4_1 copy kernels

* llama-bench : support type_k/type_v

* metal : use mm kernel only for quantum KV cache

* cuda : add comment

* llama : remove memory_f16 and kv_f16 flags

---------

Co-authored-by: slaren <slarengh@gmail.com>

* readme : add API change notice

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-07 13:03:17 +02:00
Hongyu Ouyang
81bc9214a3
train : fix #4227 (double free in examples/train-text-from-scratch/train-text-from-scratch.cpp) (#4351)
On commit b1108 (44c117f4) xaedes added

    ggml_allocr * alloc = NULL;

    ... (many lines in between)

    if (alloc) {
        ggml_allocr_free(alloc);
    }

Which is correct, but it's easy to lose context after many lines in between.

On commit b1287 (0e76a899) xaedes made a big change. From here on, alloc is freed eagerly.

    alloc = ggml_allocr_new(...)
    ... (short lines of code)
    ggml_allocr_free(alloc)

This happens a few times, but alloc is never set to NULL, and many lines below,
we still have

    if (alloc) {
        ggml_allocr_free(alloc);
    }

which causes a double-free.
2023-12-07 12:25:22 +02:00
Georgi Gerganov
05cd6e5036
server : recognize cache_prompt parameter in OAI API (#4347) 2023-12-06 20:21:59 +02:00
stduhpf
da5eaef1f3
speculative : support --color (#4343)
* speculative: add some colors

* minor : add braces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-06 10:08:17 +02:00
MaggotHATE
52c8bc3cf3
sampling : custom samplers order (#4285)
* Samplers sequence order w parameter

* Cleaned commented code

* Fixed formatting

* Rewrote with unordered_map

* Revert and rewrite, too many problems and safeguards would be needed

* Fixed code style

* Code style fixes according to review

* More readable samplers input string, fixed help

* Style fix in sampler_queue

* Formatting fixes

* Fixing whitespaces
2023-12-05 12:05:51 +02:00
Daniel Bevenius
23b5e12eb5
simple : update error message for KV cache check (#4324)
This commit updates the error message that is printed when the
KV cache is not big enough to hold all the prompt and generated
tokens. Specifically it removes the reference to n_parallel and
replaces it with n_len.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2023-12-04 18:04:21 +02:00
Miwa / Ensan
d208995c6d
swift : fix concatenation method to avoid invalid UTF8 stringfication (#4325) 2023-12-04 18:03:49 +02:00
Miwa / Ensan
5c9f90cba1
swift : fix prompt tokenization logic (#4321) 2023-12-04 15:43:45 +02:00
Ed Lee
33e171d1e9
server : fix OpenAI API stop field to be optional (#4299)
(cherry picked from commit Mozilla-Ocho/llamafile@e8c92bcb84)
2023-12-03 11:10:43 +02:00
Rickard Edén
6949b50df5
py : add grammar to oai like api (#4294) 2023-12-03 11:03:25 +02:00
Georgi Gerganov
d5a1cbde60
llama : support optional tensors (#4283) 2023-12-01 20:35:47 +02:00
Miwa / Ensan
b220222a64
swift : fix token_to_piece implementation (#4278)
* Fix token_to_piece implementation in Swift

* Fix errors
2023-12-01 20:19:45 +02:00
Georgi Gerganov
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
* metal : implement soft_max_ext

* cuda : implement soft_max_ext

* ggml : implement soft_max_ext (CPU)

* batched-bench : print threads

ggml-ci

* metal : simplify soft_max encoding

ggml-ci

* cuda : use 512 threads for soft_max instead of 32

* ggml : update soft max cpu

* cuda : do warp-based block reduce

* cuda : increase max block size to 1024

* cuda : fix warp reduction initialization of shared mem

* metal : warp-based reduction for soft max kernel

* metal : warp-based reduce for rms_norm

* metal : simplify soft max kernel

ggml-ci

* alloc : fix build with debug
2023-12-01 10:51:24 +02:00
Ziad Ben Hadj-Alouane
1d144112c0
server : add --log-disable to disable logging to file (#4260)
* * add --log-disable to disable logging to file in the server example

* * typo fix
2023-12-01 00:25:49 +02:00
Ziad Ben Hadj-Alouane
f43f09366d
server : add single-client multi-prompt support (#4232)
* * add multiprompt support

* * cleanup

* * more cleanup

* * remove atomicity of id_gen, and change lock_guard to unique_lock on completion requests

* * remove all references to mutex_multitasks

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update examples/server/server.cpp

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* * change to set

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2023-12-01 00:25:04 +02:00
John
33c9892af5
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
* ShareGPT4 compatibility (vision encoder only loading)

Load only a CLIP vision encoder (as supplied by ShareGPT finetunes)
Corrects the argument parsing for --img_mean and --img_std (which were previously not parsed but attempted to access)
Defines defaults for img_mean and img_std which are equal to the llava 1.5 CLIP encoder, so you do not have to provide them

* Update convert-image-encoder-to-gguf.py
2023-11-30 23:11:14 +01:00
Andrew Godfrey
8efa0f6ebe
main : pass LOG_TEE callback to llama.cpp log (#4033)
* main : Call llama_log_set to use LOG_TEE

* tabs to spaces
2023-11-30 23:56:19 +02:00
Miwa / Ensan
bde629bb53
batched.swift : update README.md (#4214)
docs: update how to run
2023-11-30 23:45:17 +02:00
rhjdvsgsgks
e2bd725f4b
py : fix oai proxy (#3972)
* fix oai proxy

fix generation not stoped while bot stop talking in chat mode

fix possible `slot_id` not exist

response for cors (and pre flight)

* oai proxy: workaround for some client (such as Chatbox)

* use stop as separator to replace hardcoded `\n`
2023-11-30 22:50:40 +02:00
Georgi Gerganov
1f5cd83275
examples : add readme files 2023-11-29 11:00:17 +02:00
Bailey Chittle
bb03290c17
examples : iOS example with swift ui (#4159)
* copy to llama.cpp as subdir

* attempt enabling metal, fails

* ggml metal compiles!

* Update README.md

* initial conversion to new format, utf8 errors?

* bug fixes, but now has an invalid memory access :(

* added O3, now has insufficient memory access

* begin sync with master

* update to match latest code, new errors

* fixed it!

* fix for loop conditionals, increase result size

* fix current workflow errors

* attempt a llama.swiftui workflow

* Update .github/workflows/build.yml

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-27 16:56:52 +02:00
Georgi Gerganov
3e73d31d9c
lookahead : support -n -1 infinite generation 2023-11-26 21:52:23 +02:00
Georgi Gerganov
922754a8d6
lookahead : add example for lookahead decoding (#4207)
* lookahead : init

* lookahead : generate and store n-grams

* lookahead : use loop instead recursion to generate n-grams

* lookahead : initial working implementation

* lookahead : filter repeating n-grams

* lookahead : use deterministic init

* lookahead : add to Makefile

* lookahead : fix a bug in the seq_id of the lookahead tokens

* lookahead : add comments

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-11-26 20:33:07 +02:00
Georgi Gerganov
af19d35734
server : OAI API compatibility (#4198)
* Add openai-compatible POST /v1/chat/completions API endpoint to server example

* fix code style

* Update server README.md

* Improve server README.md

* Fix server.cpp code style according to review

* server : some style changes

* server : indentation

* server : enable special tokens during tokenization by default

* server : minor code style

* server : change random string generator

* straightforward /v1/models endpoint

---------

Co-authored-by: kir-gadjello <111190790+kir-gadjello@users.noreply.github.com>
Co-authored-by: Tobi Lütke <tobi@Tobis-MacBook-Pro.local>
2023-11-25 11:29:06 +02:00
eastriver
2568a4bf54
main.swift : fix eos checking (#4197)
llama_token_eos(const struct llama_model *) is currently getting struct llama_context type variable context as a parameter.
2023-11-24 11:25:10 +02:00
Haohui Mai
55978ce09b
Fix incorrect format strings and uninitialized variables. (#4133)
* Fix incorrect format strings and uninitialized variables.

* Address comments

* Add the missing include statement
2023-11-23 22:56:53 +01:00
Georgi Gerganov
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
* llama : keep track of used KV cells + better KV cache management

* llama : zero KV cache used upon clear

ggml-ci

* llama : allow exporting a view of the KV cache (#4180)

* Allow exporting a view of the KV cache

* Allow dumping the sequences per cell in common

* Track max contiguous cells value and position as well

* Fix max contiguous empty cells index calculation

Make dump functions deal with lengths or sequences counts > 10 better

* Fix off by one error in dump_kv_cache_view

* Add doc comments for KV cache view functions

Eliminate cell sequence struct; use llama_seq_id directly

Minor cleanups

* common : add -dkvc arg for enabling kv cache dumps

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
2023-11-23 19:07:56 +02:00
Daniel Bevenius
9d5949f04b
examples : fix typo in parallel example doc comment (#4181)
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2023-11-23 13:34:20 +02:00
Galunid
0b871f1a04
finetune - update readme to mention llama support only (#4148) 2023-11-20 19:30:00 +01:00
Seb C
881800d1f0
main : Add ChatML functionality to main example (#4046)
Co-authored-by: Sebastian Cramond <sebby37@users.noreply.github.com>
2023-11-20 14:56:59 +01:00
Branden Butler
40a34fe8d0
speculative : fix prompt tokenization in speculative example (#4025)
* Support special tokens and not adding BOS to prompt in speculative

* Adapt to new should_add_bos function

* Ensure tgt and dft have same add_bos setting
2023-11-20 11:50:04 +02:00
Georgi Gerganov
dae06c06e5
Revert "finetune : add --n-gpu-layers flag info to --help (#4128)"
This reverts commit 05e8301e45.
2023-11-19 19:16:07 +02:00
Clark Saben
05e8301e45
finetune : add --n-gpu-layers flag info to --help (#4128) 2023-11-19 18:56:38 +02:00
SoftwareRenderer
936c79b227
server : relay error messages (#4131) 2023-11-19 18:54:10 +02:00
Kerfuffle
28a2e6e7d4
tokenize example: Respect normal add BOS token behavior (#4126)
Allow building with Makefile
2023-11-18 14:48:17 -07:00
Georgi Gerganov
5ad387e994
tokenize : fix trailing whitespace 2023-11-17 18:01:38 +02:00
zakkor
2fa02b4b3d
examples : add tokenize (#4039) 2023-11-17 17:36:44 +02:00
Huawei Lin
c7cce1246e
llava : fix compilation warning that fread return value is not used (#4069) 2023-11-17 17:22:56 +02:00
Jiří Podivín
f7d5e97542
py : remove superfluous import statements (#4076)
Signed-off-by: Jiri Podivin <jpodivin@gmail.com>
Co-authored-by: Jiri Podivin <jpodivin@redhat.com>
2023-11-17 17:20:53 +02:00
Jiří Podivín
ba4cf5c0bf
train : move number of gpu layers argument parsing to common/train.cpp (#4074)
- introduces help entry for the argument
 - cuts '--gpu-layers' form in order to simplify usage and documentation.

Signed-off-by: Jiri Podivin <jpodivin@gmail.com>
Co-authored-by: Jiri Podivin <jpodivin@redhat.com>
2023-11-17 17:19:16 +02:00
Andrew Godfrey
947f64f163
finetune : zero the loraB initial vectors (#4082)
* finetune : zero the loraB initial vectors

Without this, the first iteration is starting out far from the base model, instead of exactly on it.
Zeroing loraB is what the paper recommends. loralib also zeroes at least one of the init vector pairs
(though it departs from the paper in using a different distribution for the other vector, in some cases).

* tabs to spaces

* Use ggml_set_zero instead of adding a new function
2023-11-17 11:23:11 +01:00
Kerfuffle
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
* gguf-py: gguf-dump: Respect --no-tensor flag in JSON mode.

* Respect add_bos_token GGUF metadata value

* gguf-py: Try to fix SpecialVocab giving up too easily for the Nth time
2023-11-16 19:14:37 -07:00
M. Yusuf Sarıgöz
bd90eca237
llava : fix regression for square images in #3613 (#4056) 2023-11-13 18:20:52 +03:00
Georgi Gerganov
4760e7cc0b
sync : ggml (backend v2) (#3912)
* sync : ggml (backend v2) (wip)

* sync : migrate examples and llama.cpp to dynamic graphs (wip)

* sync : update tests + fix max op params to 64

ggml-ci

* sync : ggml-cuda

ggml-ci

* llama : fix save/load state context size

ggml-ci

* sync : try to fix build on tvOS

* sync : pass custom graph sizes in training examples

* sync : update graph copies to new ggml API

* sync : update sync-ggml.sh with new files

* scripts : fix header in sync script

* train : fix context size calculations

* llama : increase inference graph size up to 4096 nodes

* train : allocate grads for backward graphs

* train : allocate grads for gb_tmp
2023-11-13 14:16:23 +02:00
Richard Kiss
532dd74e38
Fix some documentation typos/grammar mistakes (#4032)
* typos

* Update examples/parallel/README.md

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
2023-11-11 23:04:58 -07:00
Alexey Parfenov
d96ca7ded7
server : fix crash when prompt exceeds context size (#3996) 2023-11-10 23:48:21 -06:00
Kerfuffle
34b0a08207
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)
* gguf-py: Refactor and add file reading support

* Replay changes from #3871

Credit to @cebtenzzre for that pull

* Various type annotation fixes.

* sort imports with isort (again)

* Fix missing return statement in add_tensor

* style cleanup with flake8

* fix NamedTuple and Enum usage

* Fix an issue with state init in GGUFReader

Move examples to an examples/ directory

Clean up examples

Add an example of modifying keys in a GGUF file

Update documentation with info on examples

Try to support people importing gguf/gguf.py directly

* Damagage is not a word.

* Clean up gguf-py/examples/modify_gguf.py whitespace

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update gguf-py/examples/modify_gguf.py formatting

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update gguf-py/gguf/gguf_reader.py type hint

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Make examples executable, formatting changes

* Add more information to GGUFReader and examples comments

* Include a gguf Python package version bump

* Add convert-gguf-endian.py script

* cleanup

* gguf-py : bump minor version

* Reorganize scripts

* Make GGUFReader endian detection less arbitrary

* Add JSON dumping support to gguf-dump.py

Which I kind of regret now

* A few for gguf-dump.py cleanups

* Murder accidental tuple in gguf-py/scripts/gguf-dump.py

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* cleanup

* constants : remove unneeded type annotations

* fix python 3.8 compat

* Set up gguf- scripts in pyproject.toml

* And include scripts/__init__.py, derp

* convert.py: We can't currently support Q8_0 on big endian.

* gguf-py: SpecialVocab: Always try available sources for special token ids

gguf-py: SpecialVocab: Try to load merges from merges.txt if not in tokenizer.json

gguf-py: SpecialVocab: Add 'add_bos_token' type bools to GGUF metadata
u

* cleanup

* Promote add_X_token to GGUF metadata for BOS and EOS

---------

Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2023-11-11 08:04:50 +03:00
Jhen-Jie Hong
4a4fd3eefa
server : allow continue edit on completion mode (#3950)
* server : allow continue edit on completion mode

* server : handle abort case in runCompletion

* server : style improvement
2023-11-10 16:49:33 -06:00
Mihai
57ad015dc3
server : add min_p param (#3877)
* Update server.cpp with min_p after it was introduced in https://github.com/ggerganov/llama.cpp/pull/3841

* Use spaces instead of tabs

* Update index.html.hpp after running deps.sh

* Fix test - fix line ending
2023-11-08 20:00:34 -06:00
xaedes
e9c1cecb9d
ggml : fix backward rope after YaRN (#3974)
* fix backward process of rope

rope backward process was broken after YaRN RoPE (#2268) implementation, due to missing changes in backward functions.

the code for the backward process is nearly identically to the forward process:
the only difference is the sign of the sin-values.

to avoid future regressions remove the near-duplicate backward functions and reuse the forward code:

for this a new function argument `bool forward` was added to `ggml_compute_forward_rope_f32` and `ggml_compute_forward_rope_f16`.
the sin-values will be negated when forward is false.

* fix finetune rope call to use correct default attn_factor of 1.0f

* remove unused `ggml_rope_xpos_back`

it is better to have only one `ggml_rope_back` function that accepts all rope parameters, so that `ggml_compute_backward` can propagate all parameters without having to switch between different rope_back variants.

* fix comments explaining the sinus sign in ggml_forward_rope

* add missing function arguments in declaration

* fix function argument type in declaration
2023-11-07 10:04:51 +02:00
Matthew Tejo
54b4df8886
Use params when loading models in llava-cli (#3976)
llava-cli was loading models with default params and ignoring settings
from the cli. This switches to a generic function to load the params
from the cli options.
2023-11-07 10:43:59 +03:00
Damian Stewart
381efbf480
llava : expose as a shared library for downstream projects (#3613)
* wip llava python bindings compatibility

* add external llava API

* add base64 in-prompt image support

* wip refactor image loading

* refactor image load out of llava init

* cleanup

* further cleanup; move llava-cli into its own file and rename

* move base64.hpp into common/

* collapse clip and llava libraries

* move llava into its own subdir

* wip

* fix bug where base64 string was not removed from the prompt

* get libllava to output in the right place

* expose llava methods in libllama.dylib

* cleanup memory usage around clip_image_*

* cleanup and refactor *again*

* update headerdoc

* build with cmake, not tested (WIP)

* Editorconfig

* Editorconfig

* Build with make

* Build with make

* Fix cyclical depts on Windows

* attempt to fix build on Windows

* attempt to fix build on Windows

* Upd TODOs

* attempt to fix build on Windows+CUDA

* Revert changes in cmake

* Fix according to review comments

* Support building as a shared library

* address review comments

---------

Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2023-11-07 00:36:23 +03:00
Thái Hoàng Tâm
bb60fd0bf6
server : fix typo for --alias shortcut from -m to -a (#3958) 2023-11-05 18:15:27 +02:00
Georgi Gerganov
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
ggml-ci
2023-11-03 09:41:56 +02:00
cebtenzzre
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
* cmake : fix build when .git does not exist

* cmake : simplify BUILD_INFO target

* cmake : add missing dependencies on BUILD_INFO

* build : link against build info instead of compiling against it

* zig : make build info a .cpp source instead of a header

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>

* cmake : revert change to CMP0115

---------

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>
2023-11-02 08:50:16 +02:00
cebtenzzre
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Jeffrey Quesnelle <jquesnelle@gmail.com>
2023-11-01 18:04:33 -04:00
Andrew Godfrey
73bdcb395e
finetune : add -ngl parameter (#3762)
* Add '-ngl' support to finetune.cpp

* Add fprintf in ggml_cuda_op_add

When I tried CUDA offloading during finetuning following the readme, I got an assert here.
This probably isn't an important case because inference later gives a warning saying you should use f16 or f32 instead when using lora

* Add 'finetune.sh', which currently fails when using GPU

"error: operator (): Finetuning on tensors with type 'f16' is not yet supported"

* tweak finetune.sh

* Suppress some warnings in ggml.c

* Add f16 implementation to ggml_compute_forward_add_f16_f32

* Add an f16 case to ggml_add_cast_impl and llama_build_lora_finetune_graphs

* finetune.sh: Edit comments

* Add "add_f16_f32_f32_cuda"

* Tweak an error message

* finetune.sh: Add an optional LLAMA_MODEL_DIR variable

* finetune.sh: Add an optional LLAMA_TRAINING_DIR variable

* train : minor

* tabs to spaces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
2023-11-01 13:49:04 +02:00
Adrian Hesketh
ca190bca8e
server : re-enable completion and embedded at the same time (#3876) 2023-11-01 11:28:28 +02:00
kalomaze
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
* Introduce the new Min-P sampler by @kalomaze
   The Min-P sampling method was designed as an alternative to Top-P, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token.

* Min-P enabled and set to 0.05 default

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
2023-10-31 20:44:49 +01:00
Kerfuffle
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
* Extend llama_kv_cache_seq_rm to allow matichng any sequence

* Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear

Use llama_kv_cache_clear for cache clearing

Change calls to llama_kv_cache_tokens_rm that want to delete by position to use llama_kv_cache_seq_rm functionality
2023-10-29 11:31:40 -06:00
Georgi Gerganov
d69d777c02
ggml : quantization refactoring (#3833)
* ggml : factor all quantization code in ggml-quants

ggml-ci

* ggml-quants : fix Zig and Swift builds + quantize tool

ggml-ci

* quantize : --pure option for disabling k-quant mixtures

---------

Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
2023-10-29 18:32:28 +02:00
Georgi Gerganov
ee1a0ec9cb
llama : add option for greedy sampling with probs (#3813)
* llama : add option for greedy sampling with probs

* llama : add comment about llama_sample_token_greedy() missing probs

* sampling : temp == 0.0 -> no probs, temp < 0.0 -> probs
2023-10-28 14:23:11 +03:00
Kerfuffle
41aee4df82
speculative : ensure draft and target model vocab matches (#3812)
* speculative: Ensure draft and target model vocab matches

* Tolerate small differences when checking dft vs tgt vocab
2023-10-28 00:40:07 +03:00
Thibault Terrasson
c8d6a1f34a
simple : fix batch handling (#3803) 2023-10-27 08:37:41 -06:00
Georgi Gerganov
34b2a5e1ee
server : do not release slot on image input (#3798) 2023-10-26 22:54:17 +03:00
Georgi Gerganov
6961c4bd0b
batched-bench : print params at start 2023-10-25 10:26:27 +03:00
cebtenzzre
ad93962657
server : add parameter -tb N, --threads-batch N (#3584) (#3768)
Co-authored-by: Michael Coppola <m18coppola@gmail.com>
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
2023-10-24 23:10:43 +03:00
Georgi Gerganov
1717521cdb
server : do not block system prompt update (#3767)
* server : do not block system prompt update

* server : update state machine logic to process system prompts

* server : minor
2023-10-24 23:08:20 +03:00
John Smith
abd21fc99f
cmake : add missed dependencies (#3763) 2023-10-24 20:48:45 +03:00
Georgi Gerganov
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
* cmake : add helper for faster CUDA builds

* batched : add NGL arg

* ggml : skip nops in compute_forward

* cuda : minor indentation

* cuda : batched cuBLAS GEMMs for src0 F16 and src1 F32 (attention ops)

* Apply suggestions from code review

These changes plus:

```c++
#define cublasGemmBatchedEx hipblasGemmBatchedEx
```

are needed to compile with ROCM. I haven't done performance testing, but it seems to work.

I couldn't figure out how to propose a change for lines outside what the pull changed, also this is the first time trying to create a multi-part review so please forgive me if I mess something up.

* cuda : add ROCm / hipBLAS cublasGemmBatchedEx define

* cuda : add cublasGemmStridedBatchedEx for non-broadcasted cases

* cuda : reduce mallocs in cublasGemmBatchedEx branch

* cuda : add TODO for calling cublas from kernel + using mem pool

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
2023-10-24 16:48:37 +03:00
Marcus Dunn
5be6c803fa
llama : remove token functions with context args in favor of model (#3720)
* added `llama_model_token_*` variants to all the `llama_token_*` functions.

* added `LLAMA_API`

* formatting

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* removed old `llama_token` functions

* changed 3 more functions to take in model

- `llama_token_get_text`
- `llama_token_get_score`
- `llama_token_get_type`

* added back docs

* fixed main.cpp

* changed token functions to use new model variants

* changed token functions to use new model variants

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-23 22:40:03 +03:00
Georgi Gerganov
438c2ca830
server : parallel decoding and multimodal (#3677)
* implementing parallel decoding in server example

* crash fixed

* save dev progress

* refactored sampling function

* completion endpoint working

* multiple client support

* grammar + no stream completion

* cached prompt support

* chat.mjs support cached prompt + some fixes

* server ui now support multiple clients

* unused change reverted

* fixed timings per slot

* add context swap

* add changes to README.md

* llava multimodal integration

* fixed tokens probs

* add multimodal input - alfa

* refactor code + remove unused comments + improved README.md

* fix compilation errors with llvm

* notify the user from server ui that multimodality is unavialable

* some ci fixes

* fix ci make build undefined ref errors

* fix long prompt than ctx proposed in #3639

* fixed premature end due stop word

* context shift fixed

* fix llava implementation

* sync README.md changes

* readme change

* update api like OpenAI

* multimodal support enabled by default

* fix make bui;d errors

* fix multiple clients

* fix zig build

* new sampling API

* latest changes of sampling API

* server : coding-style normalization

* server : coding-style normalization (part 2)

* server : remove beam-search functionality

* server : bug fix in ingest_images

n_tokens is incremented internally by llama_batch_add

* server : use refs + use llama_batch_clear()

* server : snake case

* server : minor sync

* added thread safe pipeline

* server : bach has to be allocated for n_parallel sequences

* server : no need for atomic int - already using mutex

* server : logs + minor code style

* server : fix multibyte handle in partial response (#3706)

* fix image load + view image in chat

* make : silence stb warnings

* clip : link to ggml, not to llama

* server : fix switch fallthrough

* server : fix crash in Debug on macOS (I have no idea why this fixes it!?)

* server : refactor ctx_sampling init + n_ctx + names

* server : bug fix for prompt caching

* Do not save/load image_data to localStorage

* editorconfig : new line in index.html

* server : completion requests remember slot_id

* Update readme to document multimodal in server

* server : minor style

* Update readme to document multimodal in server

* server : hide ctx_sampling->prev behind API (#3696)

* server : apply fix from #3722

* server : fix slot reuse

* server : add comment about changing slot_state to bool

---------

Co-authored-by: FSSRepo <go778sgt@gmail.com>
Co-authored-by: Damian Stewart <d@damianstewart.com>
Co-authored-by: Steward Garcia <57494570+FSSRepo@users.noreply.github.com>
Co-authored-by: Jhen-Jie Hong <iainst0409@gmail.com>
Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
2023-10-22 22:53:08 +03:00