Commit Graph

169 Commits

Author SHA1 Message Date
fairydreaming
807b0c49ff
Inference support for T5 and FLAN-T5 model families (#5763)
* llama : add inference support and model types for T5 and FLAN-T5 model families

* llama : add new API functions to support encoder-decoder models: llama_encode(), llama_model_has_encoder(), llama_model_decoder_start_token()

* common, llama-cli, llama-batched : add support for encoder-decoder models

* convert-hf : handle shared token embeddings tensors in T5Model

* convert-hf : add support for SentencePiece BPE tokenizer in T5Model (for Pile-T5 models)

* convert-hf : add MT5ForConditionalGeneration and UMT5ForConditionalGeneration to architectures supported by T5Model

* convert : add t5 tokenizer tests, use "slow" HF tokenizer for t5

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-04 15:46:11 +02:00
MistApproach
a27152b602
fix: add missing short command line argument -mli for multiline-input (#8261) 2024-07-02 22:56:46 +02:00
Xuan Son Nguyen
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
* preserve new line llama_chat_format_single

* disable chat template if in-prefix/suffix is set

* remove redundant change
2024-06-30 20:27:13 +02:00
Sigbjørn Skjæret
38373cfbab
Add SPM infill support (#8016)
* add --spm-infill option

* support --spm-infill

* support --spm-infill
2024-06-28 12:53:43 +02:00
Xuan Son Nguyen
16791b8f0b
Add chatml fallback for cpp llama_chat_apply_template (#8160)
* add chatml fallback for cpp `llama_chat_apply_template`

* remove redundant code
2024-06-27 18:14:19 +02:00
jukofyork
97877eb10b
Control vector loading fixes (#8137)
* Fixed leak in llama_control_vector_load_one() and allow llama_control_vector_load() to grow

* refactored `llama_control_vector_load_one()`

* allow multiple directions for same layer in same file

* llama_control_vector_load_one() and llama_control_vector_load() now break on error

* removed unnecessary ggml_free() call
2024-06-27 16:48:07 +02:00
Xuan Son Nguyen
49c03c79cd
cvector: better prompt handling, add "mean vector" method (#8069)
* remove completions file

* fix inverted vector

* add mean method

* code style

* remove inverted pca hotfix
2024-06-25 13:59:54 +02:00
Xuan Son Nguyen
48e6b92cc3
Add chat template support for llama-cli (#8068)
* add chat template support for llama-cli

* add help message

* server: simplify format_chat

* more consistent naming

* improve

* add llama_chat_format_example

* fix server

* code style

* code style

* Update examples/main/main.cpp

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-06-25 21:56:49 +10:00
HatsuneMikuUwU33
f702a90e24
Update control vector help (#8104) 2024-06-25 10:44:48 +02:00
Yann Follet
646ef4a9cf
embedding : more cli arguments (#7458)
* add parameters for embeddings
--embd-normalize
--embd-output-format
--embd-separator
description in the README.md

* Update README.md

fix tipo

* Trailing whitespace

* fix json generation, use " not '

* fix merge master

* fix code formating
group of parameters // embedding
print usage for embedding parameters

---------

Co-authored-by: Brian <mofosyne@gmail.com>
2024-06-24 08:30:24 +03:00
Xuan Son Nguyen
3e58b0ee35
cvector: fix CI + correct help message (#8064)
* cvector: fix CI + correct help message

* also correct --pca-iter
2024-06-22 18:11:30 +02:00
Douglas Hanley
80ea089d77
llama : allow pooled embeddings on any model (#7477)
* create append_pooling operation; allow to specify attention_type; add last token pooling; update examples

* find result_norm/result_embd tensors properly; update output allocation logic

* only use embd output for pooling_type NONE

* get rid of old causal_attn accessor

* take out attention_type; add in llama_set_embeddings

* bypass logits when doing non-NONE pooling
2024-06-21 08:38:22 +03:00
Johannes Gäßler
abd894ad96
common: fix warning (#8036)
* common: fix warning

* Update common/common.cpp

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

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-06-20 16:40:13 +02:00
Xuan Son Nguyen
0c7b3595b9
Add cvector-generator example (#7514)
* add control-vector-generator

* calc diff

* add comments

* proof-of-concept stdlib implementation

Implements PCA and file writing using mostly standard libraries. The output is recognized as a functional control vector, but outputs gibberish.

* param parsing, refactor, comments

Added basic command-line parameters for outfile and one each positive/negative prompt.

Refactored some messy code in PCA computation and GGUF exporting.

Left a bunch of comments regarding further work needed.

* example template completions

Implements an example template set built from the positive/negative prompts like the control vector Python implementation.

* add multi prompts, multi-thread for PCA

* fix mem error

* add debugs

* fix matrix transpose multiplication

you have got to be kidding me

* preliminary template/multiprompt support

model is running out of context and that ought to be fixed (segfaulting) but other than that it looks goodish

* fix zero output & param parsing, functional templating

fixed a bug where the output file had no tensor data/was all zero

fixed a bug where single hyphen flags were not being correctly parsed

implements creation of templated prompts from input (still need to adapt based on model)

* fix square_diff matmul index range and CRLF->LF line endings

fixed a logic error where square_diff would not multiply all rows

fixed a formatting error where the provided completions.txt had CRLF line endings

* add command-line args for num threads, num completions file lines, always reload model

refactored a few things and did what the commit message says on the tin

* code aestheticization

* fix compiler warnings

* in-series multithreading for prompt embedding?

added commented-out code to attempt to start implementing mutlithreading for embedding in main

* remove unnecessary multithreading

* interim fix memory leak

* translated everything but PCA (I think)

* tentatively translate the rest

* fix ggml errors and make new ones

at least it compiles and runs

* fix cb_eval

* temporary commit while I move dev environments

it finally outputs a functioning control vector - "functioning" in the sense that it can be loaded and it clearly has the right idea, but makes the model incoherent

* update debug statements

* pre-tokenize so we can allocate correct memory to ctx_diffs_wrapped

* update comments

* (wip) refactor

* clean up PCA ggml implementation

* fix shape of v_diff_original

* add n_batch for pca

* working version

* remember to copy back the last_eigenvector

* fix n_completions

* bring back n_completions

* default n_pca_batch to 20

* fix macos build

* add to makefile all targets

* use ggml_format_name

* add readme

* fix .editorconfig

* use ggml_backend_tensor_copy

* attemp to fix compile problem on mac

* fix compile warn

* reuse allocr

* move param parser to common

* better error handling

* clean up a bit

* add print_usage

* shorten help msg

* beautify help msg

* escape prompt by default

* change compile target to llama-cvector-generator

* typo

* disable GPU for PCA

* code style

---------

Co-authored-by: Christian Zhou-Zheng <christianzhouzheng@gmail.com>
2024-06-15 18:53:40 +02:00
Olivier Chafik
d4d915d351
url: save -mu downloads to new cache location (#7826)
* url: save -mu download to new cache location

* url: fs_get_cache_file_path util

* url: tweak sig of fs_get_cache_file
2024-06-08 21:21:08 +02:00
sasha0552
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
* server : Smart selection of available slot using Longest Common Substring

* add usage

* remove trailing whitespaces

* Use Longest Common Prefix (LCP) instead of LCS

* Rename argument
2024-06-08 10:50:31 +03:00
Georgi Gerganov
ee459f40f6
server : fix --threads-http arg (#7801) 2024-06-06 19:19:59 +03:00
Georgi Gerganov
f83351f9a6
imatrix : migrate to gpt_params (#7771)
* imatrix : migrate to gpt_params

ggml-ci

* imatrix : add --save-frequency cli arg

* common : fix --no-ppl
2024-06-06 16:30:58 +03:00
Georgi Gerganov
1442677f92
common : refactor cli arg parsing (#7675)
* common : gpt_params_parse do not print usage

* common : rework usage print (wip)

* common : valign

* common : rework print_usage

* infill : remove cfg support

* common : reorder args

* server : deduplicate parameters

ggml-ci

* common : add missing header

ggml-ci

* common : remote --random-prompt usages

ggml-ci

* examples : migrate to gpt_params

ggml-ci

* batched-bench : migrate to gpt_params

* retrieval : migrate to gpt_params

* common : change defaults for escape and n_ctx

* common : remove chatml and instruct params

ggml-ci

* common : passkey use gpt_params
2024-06-04 21:23:39 +03:00
Georgi Gerganov
554c247caf
ggml : remove OpenCL (#7735)
ggml-ci
2024-06-04 21:23:20 +03:00
0cc4m
3d7ebf6312
Vulkan Mixture of Experts (MoE) support (#7628)
* Finish Vulkan mul_mat_id implementation

* Add Vulkan sum_rows and div ops

* Fix MUL_MAT_ID matrix matrix shader

* Fix MUL_MAT_ID matrix vector shader dispatch size

* Fix MUL_MAT_ID matrix vector shader and dispatch code

* Update Vulkan CPU offload for MUL_MAT_ID

* Fix crash when using split mode none and setting a main GPU
2024-06-03 10:59:14 +02:00
Brian
d298382ad9
main: replace --no-special with --special (#7534)
This also flips the default behavior of the output to not include control token by default.
2024-05-27 00:10:17 +10:00
Justine Tunney
00c6390793
main : don't print special tokens with --grammar (#6923)
* main : don't print special tokens with --grammar

The CLI interface was recently changed to print special control tokens
like the </s> stop message one. This token shouldn't be printed if the
grammar flag was passed, unless the grammar specifies it, because that
breaks shell-scriptability.

* main: use seperate stream for control characters

* main: use dprintf and add --ctrl-token-no-out and --ctrl-token-fd-out

* main: dprintf isn't part of the IEEE POSIX standard. Just use write().

* main: remove --ctrl-token-fd-out in favor for fcntl() based detection

* common.cpp: accidentally removed --interactive-first

* main: only merge stdout and control token if not in conversation or grammar mode

* main: rejig control token descriptor handling

* main: must check pipe status on very top of program

* main: renamed --no-special from  --ctrl-token-no-out and other refactoring

* main: refactor ctrl_token_no_out --> no_special

* llama: rename llama_token_is_control_token() to llama_token_is_control()

* main: remove special token file descriptor feature (#5)

---------

Co-authored-by: Brian <mofosyne@gmail.com>
2024-05-25 19:04:03 +10:00
Masaya, Kato
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
* Add SVE support for q4_0_q8_0 q8_0_q8_0

* remove ifdef
2024-05-25 11:42:31 +03:00
Xuan Son Nguyen
902184dd3a
fix missing slash in fs_get_cache_directory() (#7503)
* fix missing slash in fs_get_cache_directory()

* use LOCALAPPDATA for fs_get_cache_directory()

* better code style
2024-05-25 13:30:59 +10:00
Georgi Gerganov
6ff13987ad
common : normalize naming style (#7462)
* common : normalize naming style

ggml-ci

* common : match declaration / definition order

* zig : try to fix build
2024-05-22 20:04:20 +03:00
Amir
11474e756d
examples: cache hf model when --model not provided (#7353)
* examples: cache hf model when --model not provided

* examples: cache hf model when --model not provided

* examples: cache hf model when --model not provided

* examples: cache hf model when --model not provided

* examples: cache hf model when --model not provided
2024-05-21 17:13:12 +03:00
Herman Semenov
359cbe3f46
ggml-quants, llama : removed excess checks (#7274) 2024-05-17 10:08:49 +03:00
Radoslav Gerganov
5e31828d3e
ggml : add RPC backend (#6829)
* ggml : add RPC backend

The RPC backend proxies all operations to a remote server which runs a
regular backend (CPU, CUDA, Metal, etc).

* set TCP_NODELAY

* add CI workflows

* Address review comments

* fix warning

* implement llama_max_devices() for RPC

* Address review comments

* Address review comments

* wrap sockfd into a struct

* implement get_alignment and get_max_size

* add get_device_memory

* fix warning

* win32 support

* add README

* readme : trim trailing whitespace

* Address review comments

* win32 fix

* Address review comments

* fix compile warnings on macos
2024-05-14 14:27:19 +03:00
Justine Tunney
4e3880978f
Fix memory bug in grammar parser (#7194)
The llama.cpp grammar parser had a bug where forgetting to add a closing
quotation mark to strings would cause parsing to crash. Anyone running a
server on a public endpoint is advised to upgrade. To reproduce this bug

    ./llamafile -m foo.gguf -p bar --grammar 'root::="'

Credit for discovering and reporting this issue goes to Eclypsium
Security Researcher Richard Johnson <Richard.johnson@eclypsium.com>.
2024-05-10 21:01:08 +10:00
HanishKVC
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
@hanishkvc added a new `--interactive-specials` flag which would allow for inserting special tokens from user side into the embedding stream.
2024-05-10 20:21:58 +10:00
Johannes Gäßler
c12452c7ae
JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143) 2024-05-08 21:53:08 +02:00
Dawid Potocki
83330d8cd6
main : add --conversation / -cnv flag (#7108) 2024-05-08 17:32:32 +03:00
viric
fcd84a0f5a
Fix Linux /sys cpu path to guess number of cores (#7064) 2024-05-04 15:26:53 +02:00
Georgi Gerganov
9c67c2773d
ggml : add Flash Attention (#5021)
* ggml : add ggml_flash_attn_ext API

* ggml : fix GQA support in ggml_flash_attn_ext

* ggml : online attention (CPU)

* metal : initial implementation

* metal : f16 precision

* metal : reduce branches

* metal : specialize for head size

* wip : 8 rows per simd group

* wip : 4 rows per simd group

* wip : template for rows per warp

* metal : parallelize across KV size

* metal : parallel reduce across heads

* metal : efficient flash_attn_f16 implementation

* metal : avoid redundant loads of the attention

* metal : scale and mask in matrix form

* metal : fix comment

* llama : avoid ggml_cast, use F32 query

* metal : add parallel reduce version (disabled)

* metal : move output into local memory + optimize

- the result from each simdgroup now stays in the registers
- significantly reduced SRAM usage
- more efficient skipping of -INF blocks
- avoid simdgroup barrier in hot loop
- add comments

* metal : add tests, fix scaling, support C > 32

* metal : improve precision

* ggml : fix f16 mad

* metal : minor

* metal : support Q > 8

* tests : add ATTN tests

* metal : disable buffer allocation logs

* tests : more

* metal : faster inner loop for C == 32

* metal : fix array initialization

* tests : ifdef

* ggml : switch to padded F16 mask for ggml_soft_max, ggml_flash_attn_ext

* ggml : fix ggml_soft_max mask requirement

* cuda : fix soft_max to use correct mask size

* cuda : add flash_attn kernel (wip)

* metal : optimize softmax for C > 32

* metal : optimize softmax

* tests : minor fix

* cuda : avoid zeroing fragments

* tests : update dims

* cuda : fix __hisinf() result check

* cuda : avoid warp_reduce for smax

* cuda : use int instead of int64_t

Noticeably improves performance (thanks to Johannes)

* cuda : make loops use the same loop values

Thanks Johannes again for the tip

* cuda : unroll some of the loops

* cuda : avoid __hisinf branches

* cuda : use half2 in softmax

* cuda : switch to 1 warp for bs > 16

* cuda : speed-up reduce part of the kernel

* cuda : unroll Q*K^T loop

* cuda : fix -INF block check

* cuda : simplify softmax

* cuda : fix matrix names

* cuda : minor

* llama : adapt to F16 KQ_pos

* llama : adapt new models to F16 KQ_mask

* ggml : fix F16 store (ARM NEON)

* llama : fix type of KQ_mask and KQ_pos

* ggml : fix CPU soft_max

* tests : add hs=256

* cuda : fix build

* metal : improve perf via smaller int registers

* cuda : adapt soft_max to F16 mask and pos

* CUDA: faster FlashAttention, kernel for bs == 1

* 16 cols for Phi-2

* no vec for hs, no hs==256 ncols==32 for Volta

* adjust kernel selection logic

* 4 warps, 256 stride for all D

* no ncols == 64

* Multiple parallel blocks for batch size 1

* fix compile warnings

* fix excessive KQ_b loads

* fix cmake build

* fix KV cache padding, NaN from INFINITY (#6438)

* llama : flash_attn cparam + fix defrag

* server: support flash_attn param

* server: bench: enable flash_attn param

* CUDA: refactor host code, dyn. par. blocks

* fix flash_attn_vec_f16 race condition

* flush softmax exp below threshold to 0

* store temp KQ in registers

* Calculate KQ as FP32 if KQV has GGML_PREC_F32

* Add __hgt2_mask implementation for CUDA 11

* fix KQ FP32 precision fpr parallel_blocks > 1

* llama-bench : add -fa,--flash-attn arg

* metal : add BS=1 kernel for flash attention (#6508)

* metal : add BS=1 kernel for flash attention (wip)

* metal : support more than 1 warps

* metal : opts

* metal : opt

* metal : switch to parallel reduce

* metal : reduce registers

* metal : simplify

* metal : initial FA vec kernel

* metal : use F32 attention accumulators

* batched-bench : add fattn arg

* llama : simplify llama_build_kv_store

ggml-ci

* llama : adapt build_olmo to changes

* ggml : fix arm fp16 store on windows

* metal : clean-up

* metal : clean-up kernel code

* metal : minor

* tests : remove benchmarks

ggml-ci

* ggml : fix avx512 const correctness

ggml-ci

* ggml : fix soft_max with bias on CPU

ggml-ci

* common : print --flash-attn in help

* ggml : fix num dimensions in ggml_flash_attn_ext

* llama : force disable flash attention for incompatible models

* ggml : ggml_soft_max support F16/F32 mask/pos

ggml-ci

* cuda : uint -> uint32_t

* cuda : "constexpr dim3" -> "const dim3"

ggml-ci

* cuda : try to fix __hgt2_mask

ggml-ci

* ggml : add TODO's for F16/F32 mask/pos support in other backends

* llama : replace bool need_kq_pos with use_alibi

* llama : prep ALiBi support for BERT models

ggml-ci

* llama : fix n_batch requirements

ggml-ci

* cont

* server : add help for --flash-attn arg

* llama : disable FA for AMD

* tests : remove TMP_ATTN_BENCH

ggml-ci

* llama : support save/load state with FA enabled

ggml-ci

* ci : add CUDA save-load-state tests

ggml-ci

* llama : llama_kv_cache_clear zeroes data + fix save-load seq

ggml-ci

* llama : fix copy-paste errors, add TODO

* llama : disallow incompatible states

* llama : update llama_state_get_size after v_trans field

* metal : remove tmp log

* llama : add static reminder for llama_state_get_size

* metal : fix max nsg

ggml-ci

* ci : fix arg order

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-04-30 12:16:08 +03:00
Olivier Chafik
8843a98c2b
Improve usability of --model-url & related flags (#6930)
* args: default --model to models/ + filename from --model-url or --hf-file (or else legacy models/7B/ggml-model-f16.gguf)

* args: main & server now call gpt_params_handle_model_default

* args: define DEFAULT_MODEL_PATH + update cli docs

* curl: check url of previous download (.json metadata w/ url, etag & lastModified)

* args: fix update to quantize-stats.cpp

* curl: support legacy .etag / .lastModified companion files

* curl: rm legacy .etag file support

* curl: reuse regex across headers callback calls

* curl: unique_ptr to manage lifecycle of curl & outfile

* curl: nit: no need for multiline regex flag

* curl: update failed test (model file collision) + gitignore *.gguf.json
2024-04-30 00:52:50 +01:00
cpumaxx
ffe666572f
llava-cli : multiple images (#6969)
Co-authored-by: root <root@nenya.lothlorien.ca>
2024-04-29 17:34:24 +03:00
Georgi Gerganov
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
* merged the changes from deepseeker models to main branch

* Moved regex patterns to unicode.cpp and updated unicode.h

* Moved header files

* Resolved issues

* added and refactored unicode_regex_split and related functions

* Updated/merged the deepseek coder pr

* Refactored code

* Adding unicode regex mappings

* Adding unicode regex function

* Added needed functionality, testing remains

* Fixed issues

* Fixed issue with gpt2 regex custom preprocessor

* unicode : fix? unicode_wstring_to_utf8

* lint : fix whitespaces

* tests : add tokenizer tests for numbers

* unicode : remove redundant headers

* tests : remove and rename tokenizer test scripts

* tests : add sample usage

* gguf-py : reader prints warnings on duplicate keys

* llama : towards llama3 tokenization support (wip)

* unicode : shot in the dark to fix tests on Windows

* unicode : first try custom implementations

* convert : add "tokenizer.ggml.pre" GGUF KV (wip)

* llama : use new pre-tokenizer type

* convert : fix pre-tokenizer type writing

* lint : fix

* make : add test-tokenizer-0-llama-v3

* wip

* models : add llama v3 vocab file

* llama : adapt punctuation regex + add llama 3 regex

* minor

* unicode : set bomb

* unicode : set bomb

* unicode : always use std::wregex

* unicode : support \p{N}, \p{L} and \p{P} natively

* unicode : try fix windows

* unicode : category support via std::regex

* unicode : clean-up

* unicode : simplify

* convert : add convert-hf-to-gguf-update.py

ggml-ci

* lint : update

* convert : add falcon

ggml-ci

* unicode : normalize signatures

* lint : fix

* lint : fix

* convert : remove unused functions

* convert : add comments

* convert : exercise contractions

ggml-ci

* lint : fix

* cmake : refactor test targets

* tests : refactor vocab tests

ggml-ci

* tests : add more vocabs and tests

ggml-ci

* unicode : cleanup

* scripts : ignore new update script in check-requirements.sh

* models : add phi-3, mpt, gpt-2, starcoder

* tests : disable obsolete

ggml-ci

* tests : use faster bpe test

ggml-ci

* llama : more prominent warning for old BPE models

* tests : disable test-tokenizer-1-bpe due to slowness

ggml-ci

---------

Co-authored-by: Jaggzh <jaggz.h@gmail.com>
Co-authored-by: Kazim Abrar Mahi <kazimabrarmahi135@gmail.com>
2024-04-29 16:58:41 +03:00
Pierrick Hymbert
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
* imatrix: save the dataset file used in the output file

* llama: support kv overrides type string string

* common: factorize KV Overrides parsing between common and server

* quantize: add imatrix n entries and dataset KV metadata
quantize: factorize KV Overrides parsing between common
#6656

* llama: remove kv override str_value initialization as it does not compile on some toolchain

* quantize: add imatrix m_last_call as `quantize.imatrix.chunks_count`

* quantize: add imatrix filename in KV

* llama: add llama_model_kv_override_free

* common: add llama_model_kv_override_free
common: free kv override if used after model loading

* llama: finally move the string KV override value to the stack

* llama : minor

* no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators.

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

* kv override: ensure string termination

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
2024-04-26 20:06:33 +02:00
slaren
017e6999b5
add basic tensor data validation function (#6884)
* add basic tensor data validation function

* add --check-tensors command line argument

tensor validation is disabled by default and can be enabled by adding
`--check-tensors` to the command line arguments.

quantize always validates tensors.
2024-04-26 18:39:58 +02:00
Kyle Mistele
37246b1031
common : revert showing control tokens by default for server (#6860)
* fix: revert showing control tokens by default

* feat: revert changes to default behavior of llama_token_to_piece; provide overridden declaration to receive "bool special" param to toggle showing control tokens

* feat: use the overridden declaration of llama_token_to_piece from common/common.cpp to specify "false" so that control tokens are not shown in chat completion responses"

* common : simplify

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-24 13:15:29 +03:00
Johannes Gäßler
28103f4832
Server: fix seed for multiple slots (#6835)
* Server: add tests for consistent results

* sampling: separate rng per sampling context
2024-04-24 11:08:36 +02:00
Georgi Gerganov
40f74e4d73
llama : add option to render special/control tokens (#6807)
* make : fix common dep on llama.h

* llama : add option to render special tokens

* readme : add API change notice

ggml-ci

* swift : fix build
2024-04-21 18:36:45 +03:00
Georgi Gerganov
aed82f6837
common : try to fix Android CI (#6780)
* common : disable get_math_cpu_count() until Android CI gets fixed

* common : another try
2024-04-20 13:27:12 +03:00
Justine Tunney
8cc91dc63c
ggml : add llamafile sgemm (#6414)
This change upstreams llamafile's cpu matrix multiplication kernels
which improve image and prompt evaluation speed. For starters, Q4_0
and Q8_0 weights should go ~40% faster on CPU. The biggest benefits
are with data types like f16 / f32, which process prompts 2x faster
thus making them faster than quantized data types for prompt evals.

This change also introduces bona fide AVX512 support since tinyBLAS
is able to exploit the larger register file. For example, on my CPU
llama.cpp llava-cli processes an image prompt at 305 tokens/second,
using the Q4_K and Q4_0 types, which has always been faster than if
we used f16 LLaVA weights, which at HEAD go 188 tokens/second. With
this change, f16 LLaVA performance leap frogs to 464 tokens/second.

On Intel Core i9-14900K this change improves F16 prompt perf by 5x.
For example, using llama.cpp at HEAD with Mistral 7b f16 to process
a 215 token prompt will go 13 tok/sec. This change has fixes making
it go 52 tok/sec. It's mostly thanks to my vectorized outer product
kernels but also because I added support for correctly counting the
number of cores on Alderlake, so the default thread count discounts
Intel's new efficiency cores. Only Linux right now can count cores.

This work was sponsored by Mozilla who's given permission to change
the license of this code from Apache 2.0 to MIT. To read more about
what's improved, and how it works, see: https://justine.lol/matmul/
2024-04-16 21:55:30 +03:00
Olivier Chafik
7593639ce3
main: add --json-schema / -j flag (#6659)
* main: add --json-schema / -j

* json: move json-schema-to-grammar to common lib

* json: fix zig build
2024-04-15 18:35:21 +01:00
Pierrick Hymbert
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
* gguf-debug: Example how to use ggml callback for debugging

* gguf-debug: no mutex, verify type, fix stride.

* llama: cv eval: move cb eval field in common gpt_params

* ggml_debug: use common gpt_params to pass cb eval.
Fix get tensor SIGV random.

* ggml_debug: ci: add tests

* ggml_debug: EOL in CMakeLists.txt

* ggml_debug: Remove unused param n_batch, no batching here

* ggml_debug: fix trailing spaces

* ggml_debug: fix trailing spaces

* common: fix cb_eval and user data not initialized

* ci: build revert label

* ggml_debug: add main test label

* doc: add a model: add a link to ggml-debug

* ggml-debug: add to make toolchain

* ggml-debug: tests add the main label

* ggml-debug: ci add test curl label

* common: allow the warmup to be disabled in llama_init_from_gpt_params

* ci: add curl test

* ggml-debug: better tensor type support

* gitignore : ggml-debug

* ggml-debug: printing also the sum of each tensor

* ggml-debug: remove block size

* eval-callback: renamed from ggml-debug

* eval-callback: fix make toolchain

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-11 14:51:07 +02:00
Jared Van Bortel
1b67731e18
BERT tokenizer fixes (#6498)
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
2024-04-09 13:44:08 -04:00
Jan Boon
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
* llama : save and restore kv cache for single seq id

* remove trailing whitespace

* respond error in case there's no space in the kv cache

* add kv seq save restore to test case

* add --slot-save-path arg to enable save restore and restrict save location

* Returning 0 for some cases, instead of asserting.

* cleanup error cases

* rename sequence state functions

* rename state get set functions

* add previous function names back in with DEPRECATED notice

* update doc

* adjust endpoints to preferred style

* fix restoring zero cell count

* handle seq rm return value

* unused param

* keep in the size check

* fix return types

* add server test case for slot save restore

* cleanup

* add cake

* cleanup style

* add special

* removing a whole sequence never fails

* move sequence state file functionality from server to llama to match session api and add version tags

* catch exceptions on save as well

* error log messages

* check types for stricter restore

* update server doc

* readme : update API changes date

* strict filename validation

* move include, reject bom as well

* also reject empty filename

* reject whitespace and trailing dot

---------

Co-authored-by: Martin Evans <martindevans@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-08 15:43:30 +03:00
Daniel Bevenius
4bcd6b959c
common: remove duplicate check for curl (#6471)
This commit removes one of the two identical checks for curl being NULL
in llama_load_model_from_url.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-04-04 09:49:21 +02:00