* 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>
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.
* 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>
* 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
* 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>
* 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>
* 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>
* 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>
* 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
* 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>
* 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`.
* 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>
* (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
* Support special tokens as reverse/anti prompt.
* Tokenize antiprompts only once.
* main : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* 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
* 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
* 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>
* 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>
* 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>
* 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>
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.
* [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
* 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>
* 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
* 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>
* 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>
* 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
* 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.
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>
* 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>
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>
* support minLength and maxLength in JSON schema grammar converter
* Update examples/json-schema-to-grammar.py
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
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>
* 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
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.
* 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>
* 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>
* 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>
* 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
* 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>
* 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>
* 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>
* 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>
* 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>
* 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>
* 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>
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>
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>
* 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
server : fix deadlock when prompt array contains strings and numbers
server : removed an unnecessary generation when generating multi-prompts
server : removed an unnecessary assert
* imatrix: adding --combine and --continue-from
* imatrix: be able to start from a specific chunk
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* 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
* 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
* 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>
* 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>
* server : fix context shift + simplify self-extend
* server : take system_tokens into account
* server : more n_past fixes
* server : rever n_past_se changes
* 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.
* 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>
* 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
* 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>
* 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>
* 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
* 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>
* 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"
* 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>
* 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>
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>
* 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>
* 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>
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>
* 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>
* 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
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>
* 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
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>
* 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
* 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>
* 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>
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>
* 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
* 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>
* 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>
* 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
* 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
* 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
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.
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.
* 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>
* 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>
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
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
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
* 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>
* Add API key authentication for enhanced server-client security
* server : to snake_case
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* 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>
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.
* 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
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>
* 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
* * 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>
* 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
* 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`
* 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>
* 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>
* 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>
* 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
- 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>
* 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
* 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
* 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>
* 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
* 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
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.
* 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>
* 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>
* 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>
* 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>
* 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
* 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>
* 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>
* 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>
* infill tokens correction
* serverinfill tokens correction
* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape
* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape
* only rm when params.escape, rm space if possible which is added back or rm added space token
* only rm when params.escape, rm space if possible which is added back or rm added space token
* Revert "only rm when params.escape, rm space if possible which is added back or rm added space token"
This reverts commit 63ba0b621f.
* fix interactive prompt escaping and fix server infill leading space handling
* rm unnecessary bool check
* process escapes for neg prompt and interactive consec prompts
* removed unneccessary static string escape
* check whether platform is 390x if yes->do not import immintrin.h
* support s390x big endian
* support --bigendian option for s390x
1. verified with baichuan7b-chat with float 16 on s390x
2. verified with baichuan7b-chat
3. verified with chinese-alpaca-2-13b-f16
* update format based on editor-config checker result
* Update convert-baichuan-hf-to-gguf.py
* 1. check in ggml.c if endianess is not match
2. update GGUF version
3. change get_pack_prefix to property
4. update information log
* always use "GGUF" as beginng of GGUF file
* Compare "GGUF" with file header char by char
1. Set GGUF_MAGIC to "GGUF" string instead of int value
2. Compare "GGUF" char by char to ensure its byte order
3. Move bytes swap code from convert.py to gguf.py write_tensor_data
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Added documentation of JSON return value of /completion endpoint
* Update examples/server/README.md
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Rewrite special token handling from #1931
* shorten param name, add st verification by type
* use offsets instead of copy by substr
* formatting, remove copying iterator on delete
* llama : normalize code-style
* swift fix
* print pfx/sfx if verb, main: split pfx input sfx
* dont add space when using special tokens
* minor : comment + spacing
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* WIP: start implementing LLaVA
* rm scratch buf for now, will revert after cleanup
* LLaVA image encoder is working. will combine with llama
* Add llava inference code, but it's buggy. debugging
* LLaVA is working e2e, needs to optimize memory allocation + cleanup
* Use ggml_allocr + rm unnecessary code
* fix: crlf -> lf
* fix: new line at EoF
* fix: trailing whitespace
* Add readme
* Update readme
* Some cleanup
* Are you happy editorconfig?
* rm unused batch image preprocessing
* rm unused import
* fix: rm designated initializers
* introduce pad-to-square mode for non-square images
* are you happy editorconfig?
* gitignore /llava
* Handle cases where image file does not exist
* add llava target to Makefile
* add support for 13b model variant
* Maybe seed is unlucky?
* Check if apples are compared to apples
* are you happy editorconfig?
* Use temperature = 0.1 by default
* command line: use gpt_params_parse()
* minor
* handle default n_predict
* fix typo
* llava : code formatting, rename files, fix compile warnings
* do not use Wno-cast-qual for MSVC
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix mirostat state when using multiple sequences
* Fix mirostat by completely refactoring sampling!
* Try to fix zig build.
* Export function to fetch/create default sampler states
Code formatting cleanups and add some comments
Silence a warning about id not being used when logging is disabled
* Apply some renaming suggestions.
Fix comments that were out of sync with the pull.
* Use more consistant naming convention for sampling contexts
* infill tokens correction
* serverinfill tokens correction
* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape
* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape
* only rm when params.escape, rm space if possible which is added back or rm added space token
* only rm when params.escape, rm space if possible which is added back or rm added space token
* Revert "only rm when params.escape, rm space if possible which is added back or rm added space token"
This reverts commit 63ba0b621f.
* fix interactive prompt escaping and fix server infill leading space handling
* rm unnecessary bool check
* vvhg-code-infill (#1)
* infill in separate example (#2)
* reverted changes to main and added infill example
* cleanup
* naming improvement
* make : add missing blank line
* fix missing semicolon
* brought infill up to current main code
* cleanup
---------
Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
* llama.cpp : split llama_context_params into model and context params
ggml-ci
* fix metal build
* fix freq_base/scale default to model value
* llama-bench : keep the same model between tests when possible
* move n_threads to llama_context_params, add n_threads_batch
* fix mpi build
* remove kv_size(), cuda scratch fixes
* remove low-vram option
* add n_threads_batch to system info, refactor to get_system_info()
* add documentation about --threads-batch to the READMEs
* llama-bench fix
* main : fix rope freq/scale warning
* llama.cpp : add llama_get_model
common : add llama_tokenize from model
* remove duplicated ctx/model functions
ggml-ci
* cuda : print total VRAM used
* fix track_max_mem in forward_batch_wo_cache_flash_attn_train
* remove unnecessary Adam(W) optimizer tensors.
reduces optimizer memory overhead from 7*modelsize to 2*modelsize.
additionally allows to optimize models with more than 2^31 parameters by replacing int with int64_t.
bumps training checkpoint file version, but old checkpoints can still be read.
new version with less tensors is saved.
* add gradient clipping to AdamW
* Fix reset of unused g->nodes and g->grads to NULL
* implement gradient checkpointing for training
reduces memory overhead from O(n_layer) to O(sqrt(n_layer))
as explained in readme of https://github.com/cybertronai/gradient-checkpointing
* remove unused compute buffer 3
* add and use function ggml_build_backward_expand to avoid stack overflows with large maximum number of nodes
GGML_API void ggml_build_backward_expand(struct ggml_context * ctx, struct ggml_cgraph * gf, struct ggml_cgraph * gb, bool keep);
* change AdamW decay parameter to work like the torch AdamW decay parameter
It is now relative to Adam learning rate `alpha*sched`.
Before that it was relative to `sched` only.
`alpha` being the maximum learning rate and `sched` being a scaling parameter in [0..1]
* change default AdamW weight decay parameter used in training to 0.1 as used in nanoGPT
* change default AdamW weight decay parameter defined in ggml to 0.0, making Adam default instead of AdamW
btw: the default weight decay parameter for torch.optim.AdamW is 0.01
* bug fixes for cross entropy loss
ggml_cross_entropy_loss: sums where not correctly added in workload of each thread
ggml_cross_entropy_loss_back: simplify backward process, reducing numerical issues
guard usage of exp f16 lookup in cross entropy by #define GGML_CROSS_ENTROPY_EXP_FP16
cross entropy loss is only used once during training, but it is quite sensitive to numerical errors introduced by exp-f16-lookup.
so exp-f16-lookup for cross entropy loss is disabled by default, trading better gradients for very slightly worse runtime performance.
* fix test-grad0 for cross_entropy_loss
the second argument to cross_entropy_loss must sum up to 1 for each row
* fix test-grad0 for soft_max
dont use only sum as aggregation, because sum of softmax is always 1 -> finite differences should not work
instead use sum(log(soft_max()*(1-eps)+eps)); use eps to avoid log(0)
* improve finite differences of test-grad0 by using double instead of float
* change cross_entropy_loss to output average over all rows
this helps keeping the loss and gradients in a sane range
* improve gradient checkpointing
sqrt(n_layers) is only the best checkpoint step when mem size of checkpoints and mem size of layers are equal.
since layers require more memory than the single-tensor-checkpoint we use, the optimal values are compute different:
```
given: n, u, v
objective: minimize(a*u+b*v) where a*b=n, a>0, b>0
b=n/a
minimize(a*u+v*n/a)
diff(a*u+v*n/a, a) = u - (v*n/a)/a
diff(a*u+v*n/a, a) == 0
u - (v*n/a)/a == 0
u == v*n/(a*a)
u*a*a = v*n
a*a = v*n/u
a = sqrt(n*v/u)
```
this change results in more checkpoints, requiring less layers to store between checkpoints, overall improving memory usage.
* disable gradient checkpointing debug output
* llama : fix rope usage in train-text-from-scratch after ChatGLM change
* add more training parameters:
--enable-restart N Only for Adam optimizer. Enable restarts of cos-decay
--disable-restart N Only for Adam optimizer. Disable restarts of cos-decay
--opt-past N Number of optimization iterations to track for delta convergence test. Disabled when zero.
--opt-delta N Maximum delta for delta convergence test. Disabled when <= zero.
--opt-max-no-improvement N Maximum number of optimization iterations with no improvement. Disabled when <= zero.
--adam-epsf N AdamW epsilon for convergence test. Disabled when <= zero.
--adam-min-alpha N Adam minimum learning rate alpha, usually 0.1 * alpha
* replace memcpy with reshape operation so that the graph is not cut at the input
this makes it possible to store other values into the input tensor and then simply recompute the graph without rebuilding it
* remove unused function argument from get_example_targets_batch
* measure and print total training time
* add optimization callback to ggml_opt_resume_g
this callback is called before each iteration with custom data and pointer to learning schedule parameter (only used in Adam(W)).
can be used for dynamic learning schedule and setting input data for batches before each iteration
* use optimization callback in training
allows dynamic learning schedule and different batch data for each iteration without relying on low n_iter and high n_examples parameters
reduces runtime by avoiding restart of optimization function and improves training convergence by providing a different batch for each iteration
* add minimum number of tensor dimensions to apply weight decay (default 2)
this allows to not apply weight decay to bias parameters
* rename training parameter cos-decay-alpha to cos-decay-min and clarify that adam-min-alpha also applies to warmup
* fix increase of model.train_samples and model.train_tokens
now that each optimizer iteration gets its own batch we need to multiply by number of opt iterations
* change sampling parameters for prediction after training to defaults of common.h
and clarify what is context for prediction and what are generated tokens
* tighten abs error bounds for cross_entropy_loss in test-grad0
* add conditional compilation of using F16 exp in flash attention
uncomment `// #define GGML_FLASH_ATTN_EXP_FP16` to enable usage of f16 exp in flash attention
* tighten abs error bounds for flash_attn in test-grad0
* tighten abs error bounds for sqrt in test-grad0
* remove out-commented vectorized code of opt_adam
the vectorized code might be bit faster for low number of parameters, but it had a big memory usage overhead
* ggml : update ggml_rms_norm_back with configurable eps
* llama training : fix ggml_rms_norm_back calls to pass configurable eps
* remove trailing whitespace
* add train function using automatic gradient checkpointing backward pass and allocator
* in train function replace add_inplace by regular add
because using add_inplace seems to result in different gradients
* don't use allocate hash_map on context
because the context has no_alloc=True when using memory allocator resulting in NULL data pointers
* correctly clone reshape and permute operations by also cloning tensor->nb values
* fix variable name and add missing type cast
* terminate recursive tensor cloning when reaching tensor without src tensors
* correctly clone view tensors by setting data pointers
without this the checkpointing would only work when being used together with memory allocator
* fix variable names
* swap arguments to commutative ops to be the same as in `forward_batch_wo_cache_flash_attn`
* add input tensors as checkpoints
so that recursive tensor cloning of gradient checkpointing terminates on input tensors
* fix variable name and add missing boolean negation
* make sure some tensors are not reallocated by inserting new temporary nodes depending on them:
output and parameter gradient tensors need to be available at the end of the graph execution
parameter gradient tensors also need to be available before the graph execution because they are set to zero before each optimizer iteration
checkpoint tensors are allocated all together to reduce memory allocator fragmentation
afterwards, in addition to the temporary nodes, we also need to reset the temporary leafs
* fix ASSERT to work with zero layers
* add training options whether to use allocator and/or unified training function
* integrate unified training function which may use memory allocator
the unified training function also supports arguments whether to use flash attention and/or gradient checkpointing
* format name of cloned tensors with " (clone)" suffix
* set names for tensors in unified train function for easier debugging
* allocate graph on context using ggml_new_graph
* remove handwritten training functions
* remove unused training parameters "use_scratch" and "use_unified"
* remove trailing whitespace
* remove unused train params: mem_compute1_gb & mem_compute2_gb
mem_compute_gb is used for compute when automatic memory allocator is not enabled, otherwise it can be very small to only hold the tensor definitions
mem_compute0_gb is used for automatic memory allocator (as long as measurement of max required size is not implemented)
* remove unused forward_batch function
* add debug asserts in ggml_allocr_alloc to some common pitfalls when using this function directly
* only use ggml_allocr_alloc when tensor has NULL data and is no view
* fix test when to create temporary backward graph
temporary backward graph is only necessary when using checkpointing
* fix memory "leak" in optimizers
each iteration a new cplan with new memory for work data was allocated.
now cplan creation only happens at the start of optimization, with each iteration reusing the cplan and its work data.
* reverse order of for loop in ggml_build_backward_expand to save memory when using gradient checkpointing and allocator
with this loop order gradient checkpointing with allocator on 16 layer model saves 13% memory; 2 layer memory it saves 2% memory.
the computation results are the same
* add API functions to access llama model tensors
* add stub example for finetuning, based on train-text-from-scratch
* move and remove code
* add API functions to access remaining model parameters:
mult, head and rot
* first draft for LORA finetune training
* remove const model and layer arguments in API functions for accessing model tensors
* bug fixes to make finetune compile
automatic allocator does not work yet
* add debug prints for training memory improvements
* fix names of lora tensors
* avoid stack overflow resulting from big ggml_cgraph
replace stack allocation and ggml_build_forward by ggml_new_graph in combination with ggml_build_forward_expand
* replace llama API functions to get model tensors by one function to get model tensor by name
LLAMA_API struct ggml_tensor * llama_get_model_tensor(struct llama_model * model, const char * name);
* remove unused call to not existing llama_get_layer_from_model
* implement ggml_compute_forward_out_prod_q_f32
* remove trailing whitespace
* add lora finetune support on quantized base model tensors
* add ggml_add_cast API function
this function works like ggml_add, but accepts a data type for the resulting tensor.
only supported for quantized src0 input.
* use ggml_add_cast in finetuning
lora-applied weights will now have data type F32, which improves gradients when finetuning quantized base models
* bug fix: actually use result type passed to ggml_add_cast
* make sure base model tensors data cannot be used in viewable operations
memory allocator would try to make lora application inplace on base model tensors.
since those are memory mapped this will result in memory access violations
* fix bug in ggml_out_prod which resulted in wrong n_dims of result tensors
* avoid keeping in memory ALL of the gradients
The problem here stems from ggml_graph_reset. This function is called in the optimization function, before each graph computation, to reset the gradients to zero. This required a unique memory slot for each gradient: allocating memory from a previosly freed memory location might lead to non-zero input gradients.
During ggml_compute_backward the gradients are build stepwise by adding or substracting new values, starting from a OP_NONE tensor which needs to contain zero-values. This requires the graph reset.
To avoid this I now remember in ggml_build_backward_expand the original OP_NONE gradient tensors in a hash table, which is passed to ggml_compute_backward. There instead of using add (or sub or similar) I test whether the existing gradient to be changed is a zero-valued-tensor by looking up its existence in the hash table. When it is such a zero-tensor it will not be modified, but replaced by the value to be added, otherwise the regular add (not inplace, allocator will take care of this) will be used. This way none of those zero-tensor values will be necessary in the final backward graph and more importantly they won't need a unique memory slot, just to make them zero.
* remove trailing whitespace
* remove debug prints and function to compute tensor data hash
* improve optimization iteration prints
* adjust maximal values to support finetuning 3B models
* change default finetune params lora_r and lora_alpha to match the n_rank parameters of 4
* bug fix: make sure finetune input gradient is allocated at begin and kept until end
* remove unnecessary src tensor from ggml_get_rows_back
we don't need data of src[2] for computation, only to setup the correct output shape.
remove dependency on src[2], so that allocator can work more freely.
the computational graph is still completely determined, because the output shape is naturally included.
this is similar to how ggml_reshape does it.
* remove unnecessary src tensor from ggml_repeat & ggml_repeat_back
we don't need data of src[1] for computation, only to setup the correct output shape.
remove dependency on src[1], so that allocator can work more freely.
the computational graph is still completely determined, because the output shape is naturally included
* resolve todo
allocator will only make it inplace when they are of the same type
* mixing multiple LORA adapters is now possible
pass more than one '--lora FNAME' argument to apply more than one LORA.
use '--lora-scaled FNAME S' when you want to specify a user-defined scale for an adapter.
* add option to save finetune output every N iterations
* also save latest finetune output with ITERATION="LATEST" and print where files are saved
saving with LATEST makes it easier to resume training from the latest checkpoint
the string "LATEST" can be configured with command line option "--fn-latest STR"
* update checkpoint train stats before saving via "--save-every"
* add command line option `--rank-wo N` for rank of wo tensor
* update finetune README
* fix dump_non_result_info_yaml to output multiple lora adapters
* bug fix: replace GGML_TYPE_SIZE[t] by ggml_type_size(t)
* replace llama_n_mult by llama_n_ff
* finetune bug fixes to compile with merged in code from master
* remove prediction related code to reduce duplicated code with main
use main instead
* reduce large memory overhead in train-text-from-scratch
all gradients had to be pinned so that graph_reset works correctly.
this is no longer necessary with the changes to ggml_compute_backward introduced in this PR.
* add comment explaining why finetune checkpoints are allocated in one block
* make default value of float member a float literal
* handle rms_norm and rope parameters the same as in train-text-from-scratch
* remove unused code
* remove vocab related code as it is unnecessary
* add LLM_KV_TRAINING_TYPE to train-text-from-scratch checkpoints
so that they can be differentiated from lora finetune checkpoints
* add gguf constants and load/save functions from train-text-from-scratch
* add load & save lora finetune checkpoints via gguf
* add python script to convert old finetune checkpoint files to gguf
* remove old checkpoint save & load code
* remove code to print data checksums which was used to verify correctness of new gguf code
* omit tokenization when training is disabled, only save llama lora adapter
training can be disabled by passing '-n 0' to finetune
* remove trailing whitespace
* update README.md
* implement ggml_compute_forward_repeat_f16
* avoid stack overflow of large cgraphs in test-grad0
* add ggml API functions ggml_unravel_index, ggml_get_i32_nd and its analogs for set and for f32
ggml_get_i32_1d, ggml_set_i32_1d, ggml_get_f32_1d, ggml_set_f32_1d now support non-contiguous tensors.
in case of non-contiguous tensor, the 1d index is unraveled into a multi index using ggml_unravel_index to be passed to '_nd' function equivalent.
this fixes a bug in test-grad0 which happens due to ggml_build_backward not building purely contiguous tensors anymore
* increase test-grad0 context mem size to accommodate for bigger cgraph
* add sanity check to ggml_compute_backward, asserting the correct shape of gradients
* fix ggml_acc_or_set to return tensor of correct shape
* remove unused 'inplace' argument from ggml_compute_backward function
inplace operations to add gradients are no longer created by ggml_compute_backward
use allocator to automatically make inplace operations
* add missing argument 'int i0' to ggml_get_i32_nd & ggml_set_i32_nd header declarations
* fix error message in ggml_allocr_alloc to display actual max_avail
* fix check_gradient
ggml_build_backward_expand was previously replaced by ggml_build_backward, but the assignment of forward graph to backward graph missing
* use tensor->view_src instead of ggml_is_view and get_view_source
* move gradient checkpointing code into ggml, new API function:
// build gradient checkpointing backward graph gb for gf using provided checkpoints
// gb_tmp will contain original backward graph with rewritten backward process nodes,
// but without the second forward pass nodes.
GGML_API void ggml_build_backward_gradient_checkpointing(
struct ggml_context * ctx,
struct ggml_cgraph * gf,
struct ggml_cgraph * gb,
struct ggml_cgraph * gb_tmp,
struct ggml_tensor * * checkpoints,
int n_checkpoints);
* replace custom data getters and setters by ggml functions
* train-text-from-scratch can train (full finetune) gguf models
just pass the gguf model via `--checkpoint-in FN`.
after this, to continue training, pass the generated checkpoint instead of the original gguf model.
tested with smaller models, bigger models may exceed available memory.
use (LORA) finetune for those.
* remove trailing whitespace
* add option to save train-text-from-scratch output every N iterations
* update README.md
* fix warnings
* fix warnings
* remove finetune option to disable allocator
the allocator should always be used.
by making sure that it is always used it gets easier to implement automatic memory requirements computation
* add tensor checkpoints only when gradient checkpointing is enabled
* initialize opt ggml context if none was provided
* add ggml-alloc API function 'ggml_allocr_max_size' to get max size of alloc
GGML_API size_t ggml_allocr_max_size(struct ggml_allocr * alloc);
* finetune: automatically allocate all memory and changes to command line options
remove '--n_examples N' parameter, as it no longer makes sense to call optimization process multiple times in a loop.
add '--only_write_lora' command line option: will skip tokenization and training, to only write a llama.cpp comptabile LORA adapter.
remove memory buffer related command line options.
improve iteration console output.
* add finetune to Makefile
* update README.md
* print time per iteration and estimate remaining time
* increase measured alloc size by tensor_alignment
ggml_allocr_reset will reduce the given size by up to tensor_alignment-1
* fix README.md
* add some more allocator debug prints
* bug fix, probably solves the 'ggml_allocr_alloc: not enough space in the buffer' issue
* revert last commit
"bug fix, probably solves the 'ggml_allocr_alloc: not enough space in the buffer' issue"
"alloc was freeing an externally allocated tensor, because it calculated the end of allocator memory as alloc->data + alloc->max_size instead of alloc->data + alloc->size."
This is intentional to reduce the risk of freeing external tensors when measuring. Unless max_size is not properly calculated, I don't see why this is an issue.
* remove unnecessary "0x" before "%p" output
* move measurement memory segment to upper region of the address space
* update README.md
* fix printf format warnings
* add missing gguf_free in load_checkpoint_lora_file
* load default rms_norm and rope parameters from base model
* add gradient accumulation
specify number accumulation steps with '--grad-acc N'.
this will simulate a bigger batch size of grad_acc*batch.
* fix tracking of train_samples and train_tokens
* build : fix compile warnings
* ggml : fix L-BFGS linesearch loop
* improve finetune time measurement
fix printf warnings on system where int64_t is (long int).
change time datatypes to double because values get big with long training times.
exclude file saving from time measurement.
converge faster to actual time per iteration by removing very small first duration before first iteration was performed.
fix bug in output of total training time, the reported value was 1000 times to small.
* specify default lora rank with '--lora-r N'
'--lora-r N' will specify default rank for all tensors
'--rank-wq N', etc. will override this default rank for specific tensor types.
* fix gradient accumulation bug where the same batch was used for each microstep
* fix gradient accumulation bug where the same batch was used for each microstep
* support grouped-query-attention in ggml_flash_attn and ggml_flash_attn_back
k and v can now be repeated in q along ne[2]
in forward pass just use modulo to compute k and v indices, like ik2 = iq2 % nek2.
in backard pass this won't work as easy, because multiple threads will compete to accumulate to the same k->grad[:,ik1,ik2,ik3] and v->grad[:,iv1,iv2,iv3].
so we change the parallelization over q rows to be over k rows. this ensures non-overlapping (ik2,ik3) across threads.
in each thread we then iterate over the number of repetitions of k/v in q to compute iq2 as iq2 = ik2 + irep*nek2.
since ne2 is not the same for q,k and v we also change how the gradients are concatenated into the result tensor.
additionally the offsets of gradq, gradk and gradv in the result tensor are now memory aligned.
we also simplify the compute_backward part of flash_attn to use ggml_reshape instead of switching over the number of dimensions.
this needs a small change to ggml_reshape, removing the assertion of second argument to be contiguous.
since only the shape (ne) of the second reshape argument is of relevance, its memory layout (nb) is irrelevant -> it can very well be non-contiguous.
change test-grad0 to also test for repeated k/v in q.
this changes the rng and now results in small gradient differences in softmax. these solely come from using f16 exp table lookup in forward softmax: when temporarily changing softmax to use actual exp function, the reported gradient differences go away. gradient differences coming solely from f16 table lookup are acceptable.
added a note to explain this.
* add llama API functions to get grouped-query-attention n_head parameter 'n_head_kv'.
* fix finetune to support grouped-query-attention (using flash-attention)
note: ggml changes to ggml_out_prod are necessary to support grouped-query-attention without flash-attention.
* support broadcastable a in out_prod(a, b) and backward pass of broadcasting mul_mat(a, b)
* test broadcasting mul_mat backward pass
* decouple random number generator of each operation test
when changing one test the rng of others tests is not influenced anymore
* add comment briefly describing what ggml_repeat_back does
* simplify broadcasting mul_mat backward using ggml_repeat_back
* add cgraph evaluation order member and corresponding enum type
this controls in which order ggml_build_forward visits source nodes.
by default the nodes are visited left to right, i.e. src[0] first.
in some cases it is beneficial for ggml-alloc to visit in a different order.
two possible orders are supported: left-to-right (src[0] first) and right-to-left (src[0] last).
* measure max compute size for each cgraph eval order and use best order
this can bring huge memory savings:
e.g. codellama-34b with n_ctx=64, n_batch=1 goes from 92927.8mb down to 4627.6 MB
* remove unused command line options
* add sample start patterns and options to force new or by default resume last shuffling
* update shuffle rng state on reshuffle
* exclude known zero values from computations in flash_attn_f32 & flash_attn_back_f32
* remove probably unnecessary exception type flags from stringstream
* pass correct max number of tokens to llama_tokenize
* account for possible leading whitespace that will be added by tokenizer
e.g. '\t' will be tokenized by llama spm tokenizer to [29871, 12]
* use unrolled vec_mad in out_prod
y is vec_mad result vec.
x is vec_mad input vec.
v is vec_mad input scalar.
ggml_vec_mad_f32_unroll will internally loop over x and v with same y.
GGML_VEC_MAD_UNROLL is by default defined to 32.
This value is empirical optimized using performance test runs of out-prod in openllama-3b finetune with 256 context length and batch size 1. It gives 23% performance boost for out_prod.
Full measurements of out-prod runtime in ms:
unroll_xv unroll_yv
1 67014.643 87826.469
2 77117.552 89077.656
4 72091.311 109121.657
8 61077.543 88678.334
16 56914.67 79514.947
24 59024.595 84350.254
28 55952.446 83368.73
32 51476.658 85177.745
36 55973.792 84659.92
40 55139.616 93844.738
48 60736.392 93330.267
64 99856.878 116994.99
Second column is when unrollying yv instead of xv
* set lora_alpha to value of lora_r if it is not set via command line
otherwise only changing lora_r will change scaling of lora adapter used in prediction
* reshuffle original sample order instead of the previous shuffled order
otherwise resumed reshuffle will not result in same sample order
* block tiling for out-prod inspired by mul-mat
block sizes are empirically optimized
roughly doubles the flops of out-prod
* exclude some more known zero values from computations in flash_attn_f32 & flash_attn_back_f32
* add static keywords
* remove outcommented old code
* update train-text-from-scratch with tokenization, sample selection and shuffling from finetune
* remove lbfgs related train parameters
* move common train functions into common/train.[h|cpp]
* move train state into struct train_state
* move train data saving code into callback to unify code of opt_callback
train_params are still different in finetune and train-text-from-scratch, so it can't yet be moved to train.h|cpp
* move common train params into common/train
* move common opt_callback into common/train
* fix consume_common_train_arg
* save and load head_count_kv in lora checkpoints
* increase train_samples by used_samples instead of number of batches
on batch can contain more than one sample when option "fill_with_next_samples" is used
* fix usage of llama_tokenize
* remove static from process_escape since we need it exposed in header
* fix code formating of long function declarations
* fix condition in load_train_state_gguf
* use die("msg") instead of replace GGML_ASSERT(!"msg") or throw std::runtime_error("msg")
* fix saving and loading of training type
* remove terminating '\0' from tokenization
(llama_tokenize is now passed the string length instead of relying on terminating '\0')
* fix compile warnings
* fix compile warnings
* use new/delete for train_state instead of malloc/free
using malloc may result in seg faults when trying to assign string fields
* assert that sample_count > 0, avoiding division by zero
* fix frand to return value in interval [0,1)
* add train option "--sample-random-offsets"
Use samples beginning at random offsets.
The offset is only applied to the first sample in each batch context window.
Together with "--fill-with-next-samples" this may help for training endless text generation.
For example given a dataset containing samples "abcd", "ABCD", "0123".
With context size of 8 and options "--fill-with-next-samples", "--no-separate-with-eos", "--no-separate-with-bos",
the context windows of batches could only be filled with "abcdABCD", "ABCDabcd", "0123abcd", etc.
With "--sample-random-offsets" it can also be filled with "23abcdAB", "bcd0123A", etc.
* deduplicate code into function
* remove n_rot hparam, as it must always be hparam.n_embd_head()
* align code
* assert correct base model tensor shapes
* move some params from lora hparams into model hparams and load model params from gguf
this equalizes the model definition in finetune and text-from-scratch and removes the need for additional llama api functions to get model parameters
* remove now unnecessary llama API functions to get model params that where added by this PR
* train-text-from-scratch: automatically allocate model tensors, remove option '--mem-model N'
* train-text-from-scratch: automatically allocate opt context
* train-text-from-scratch: automatically allocate input tensors
* train-text-from-scratch: automatically allocate compute memory
* remove unused options and equalize train-text-from-scratch with finetune
* initialize opt->loss_after with zero
* add export-lora program
* remove trailing whitespace
* add export-lora build in Makefile
* remove unused struct tensor_info from export-lora
* add export-lora build dependency to llama
because it depends on common, which depends on llama
* update finetune README.md
* cancel optimization when specified number of epochs is completed
* improve handling of export-lora arguments
print errors and warnings when files could not be read or created
* Fix export-lora.cpp "not enough space in the context's memory pool" (#1)
* Fix export-lora.cpp "not enough space in the context's memory pool"
Without this patch, export-lora would sometimes error with "not enough space in the context's memory pool (needed 656784, available 656800)".
* increase required context size by 5*GGML_MEM_ALIGN instead of plain 16
---------
Co-authored-by: xaedes <xaedes@gmail.com>
* improve handling of not yet supported tensor types
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: meatbag-18a <145869052+meatbag-18a@users.noreply.github.com>
* Resync my fork with new llama.cpp commits
* examples : rename to use dash instead of underscore
* New model conversions
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix für #2721
* Reenable tokenizer test for LLaMa
* Add `console.cpp` dependency
* Fix dependency to `common`
* Fixing wrong fix.
* Make console usage platform specific
Work on compiler warnings.
* Adapting makefile
* Remove trailing whitespace
* Adapting the other parts of the makefile
* Fix typo.
* Fixing the last deviations from sentencepiece indicated by test-tokenizer-1
* Simplify logic
* Add missing change...
* Fix ugly compiler warning
* llama_tokenize should accept strings containing NUL now
* Adding huichen's test case
