]>
git.djapps.eu Git - pkg/ggml/sources/llama.cpp/log
Georgi Gerganov [Mon, 22 Apr 2024 12:41:11 +0000 (15:41 +0300)]
llama : fix typo in <|im_end|> token text (#6745)
Pierrick Hymbert [Mon, 22 Apr 2024 11:22:54 +0000 (13:22 +0200)]
ci: fix job are cancelling each other (#6781)
github-actions[bot] [Sun, 21 Apr 2024 00:17:47 +0000 (00:17 +0000)]
flake.lock: Update
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/
1042fd8b148a9105f3c0aca3a6177fd1d9360ba5 ?narHash=sha256-3sbWO1mbpWsLepZGbWaMovSO7ndZeFqDSdX0hZ9nVyw%3D' (2024-04-10)
→ 'github:NixOS/nixpkgs/
5c24cf2f0a12ad855f444c30b2421d044120c66f ?narHash=sha256-XtTSSIB2DA6tOv%2Bl0FhvfDMiyCmhoRbNB%2B0SeInZkbk%3D' (2024-04-19)
Olivier Chafik [Sun, 21 Apr 2024 17:48:53 +0000 (18:48 +0100)]
`build`: generate hex dump of server assets during build (#6661)
* `build`: generate hex dumps of server assets on the fly
* build: workaround lack of -n on gnu xxd
* build: don't use xxd in cmake
* build: don't call xxd from build.zig
* build: more idiomatic hexing
* build: don't use xxd in Makefile (od hackery instead)
* build: avoid exceeding max cmd line limit in makefile hex dump
* build: hex dump assets at cmake build time (not config time)
Georgi Gerganov [Sun, 21 Apr 2024 15:36:45 +0000 (18:36 +0300)]
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
Georgi Gerganov [Sun, 21 Apr 2024 13:47:57 +0000 (16:47 +0300)]
ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
Wouter [Sun, 21 Apr 2024 13:03:39 +0000 (15:03 +0200)]
llama : add llama-3 chat template (#6751)
* Added llama-3 chat template
* Update llama.cpp
Co-authored-by: Samuel Tallet <redacted>
* Update llama.cpp
Co-authored-by: Samuel Tallet <redacted>
* Update tests/test-chat-template.cpp
Co-authored-by: Samuel Tallet <redacted>
* Added EOS stop sequence according to https://github.com/ggerganov/llama.cpp/pull/6751#issuecomment-
2065602862
* Removed adding of BOS token before first message
* Removed bos token from expected output from llama-3
* Update tests/test-chat-template.cpp
Co-authored-by: Rene Leonhardt <redacted>
* Update tests/test-chat-template.cpp
Co-authored-by: Rene Leonhardt <redacted>
* Added <|end_of_text|> as another stop token
* Reverted last change of adding the end_of_text stop word for llama 3
---------
Co-authored-by: Wouter Tichelaar <redacted>
Co-authored-by: Samuel Tallet <redacted>
Co-authored-by: Rene Leonhardt <redacted>
Co-authored-by: Georgi Gerganov <redacted>
pmysl [Sun, 21 Apr 2024 12:49:30 +0000 (14:49 +0200)]
gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
Jan Boon [Sun, 21 Apr 2024 12:35:40 +0000 (20:35 +0800)]
doc : add link to falcon (#6789)
Mohammadreza Hendiani [Sun, 21 Apr 2024 12:32:05 +0000 (16:02 +0330)]
readme : add Fedora instructions (#6783)
* added fedora to list of distros that may need the package (the packages have the same name on Fedora)
* how to add clblast that is avalible in the fedora repos
Justine Tunney [Sun, 21 Apr 2024 12:19:04 +0000 (08:19 -0400)]
llava : use logger in llava-cli (#6797)
This change removes printf() logging so llava-cli is shell scriptable.
Pedro Cuenca [Sun, 21 Apr 2024 11:50:41 +0000 (13:50 +0200)]
llama : support Llama 3 HF conversion (#6745)
* Support Llama 3 conversion
The tokenizer is BPE.
* style
* Accept suggestion
Co-authored-by: Sourab Mangrulkar <redacted>
* llama : add llama_token_is_eog()
ggml-ci
* llama : auto-detect more EOT tokens when missing in KV data
* convert : replacing EOS token is a hack
* llama : fix codegemma EOT token + add TODOs
* llama : fix model type string for 8B model
---------
Co-authored-by: Sourab Mangrulkar <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Jan Boon [Sat, 20 Apr 2024 16:29:50 +0000 (00:29 +0800)]
doc : server tests require llama to be built with curl enabled (#6788)
Georgi Gerganov [Sat, 20 Apr 2024 10:27:12 +0000 (13:27 +0300)]
common : try to fix Android CI (#6780)
* common : disable get_math_cpu_count() until Android CI gets fixed
* common : another try
loonerin [Fri, 19 Apr 2024 17:03:35 +0000 (13:03 -0400)]
ci: add ubuntu latest release and fix missing build number (mac & ubuntu) (#6748)
Pierrick Hymbert [Fri, 19 Apr 2024 11:19:01 +0000 (13:19 +0200)]
server: static: upstream upgrade (#6765)
nopperl [Fri, 19 Apr 2024 09:35:54 +0000 (09:35 +0000)]
Implement the OLMo architecture (#6741)
* implement olmo architecture
* remove unused variable
* remove unused moe branch
* remove check for weight
* remove superfluous moe, bias and rope tensors
* clarified comment
* fix clamp_kqv setting
* remove obsolete parameter name filter
Austin [Fri, 19 Apr 2024 07:16:45 +0000 (03:16 -0400)]
train : add general name (#6752)
* llama : make general.name optional
* train: Add 'general.name' to model metadata
Signed-off-by: teleprint-me <redacted>
---------
Signed-off-by: teleprint-me <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Neo Zhang [Fri, 19 Apr 2024 01:16:31 +0000 (09:16 +0800)]
fix wrong parameter in cmd in readme-sycl.md (#6755)
Co-authored-by: jianyuzh <redacted>
slaren [Thu, 18 Apr 2024 13:18:48 +0000 (15:18 +0200)]
ggml : group all experts in a single ggml_mul_mat_id (#6505)
* ggml : group all experts in a single ggml_mul_mat_id
cuda : improve mmid row copy
* cuda : fix bin bcast with non-cont src0
* test-backend-ops : only run all mul mat tests for base types
* llama : disable moe offloading with SYCL
---------
Co-authored-by: Georgi Gerganov <redacted>
Sigbjørn Skjæret [Thu, 18 Apr 2024 11:49:01 +0000 (13:49 +0200)]
convert : support models with multiple chat templates (#6588)
* Support converting models with multiple chat templates
Adds the following metadata:
* tokenizer.chat_templates
* tokenizer.chat_template.<name1>
* tokenizer.chat_template.<name2>
* tokenizer.chat_template.<...>
Where `tokenizer.chat_templates` is an array of the template names (except `default`), `default` is added to the regular `tokenizer.chat_template`.
* replace filtered characters with underscore
* New script to add/modify/remove metadata
This scripts creates a copy of a GGUF file and allows you to add/modify/remove metadata in the process.
Most importantly this allows you to update chat templates, either as a string or directly from an updated tokenizer_config.json file.
* Add files via upload
add new script to project/readme
* flake--
Ren Xuancheng [Thu, 18 Apr 2024 11:38:04 +0000 (19:38 +0800)]
Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)
slaren [Thu, 18 Apr 2024 07:04:47 +0000 (09:04 +0200)]
llama : fix compatibility with old 2 expert models (#6735)
Georgi Gerganov [Wed, 17 Apr 2024 20:58:26 +0000 (23:58 +0300)]
llamafile : tmp disable + build sgemm.o when needed (#6716)
* build : sgemm.o only when needed
ggml-ci
* llamafile : tmp disable due to MoE bug
ggml-ci
Yaroslav [Wed, 17 Apr 2024 12:47:50 +0000 (14:47 +0200)]
readme : add UI (#6724)
* Update README.md
* Update README.md
---------
Co-authored-by: Georgi Gerganov <redacted>
Zheng.Deng [Tue, 16 Apr 2024 20:51:07 +0000 (04:51 +0800)]
convert : fix autoawq gemma (#6704)
* fix autoawq quantized gemma model convert error
using autoawq to quantize gemma model will include a lm_head.weight tensor in model-00001-of-00002.safetensors. it result in this situation that convert-hf-to-gguf.py can't map lm_head.weight. skip loading this tensor could prevent this error.
* change code to full string match and print necessary message
change code to full string match and print a short message to inform users that lm_head.weight has been skipped.
---------
Co-authored-by: Zheng.Deng <redacted>
Georgi Gerganov [Tue, 16 Apr 2024 20:50:38 +0000 (23:50 +0300)]
llama : make general.name optional (#6709)
Georgi Gerganov [Tue, 16 Apr 2024 20:50:22 +0000 (23:50 +0300)]
ggml : fix llamafile sgemm wdata offsets (#6710)
ggml-ci
Justine Tunney [Tue, 16 Apr 2024 18:55:30 +0000 (14:55 -0400)]
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/
Ashish [Tue, 16 Apr 2024 15:48:35 +0000 (08:48 -0700)]
llama : add StableLM2 12B (#6635)
* StableLM2 12B support for huggingface -> GGUF
* StableLM12 tensormapping and constants
* StableLM-2-12b model support
* fix
* Added 12B support
* Removed autoformatting; resolved bug where model_arch was not selecting StableLM2
* Formatting
* Do QK norm stacking in model conversion step
* Converge StableLM and StableLM2 code to simplify graph construction
* Fix accidental removal
* Removed warnings
* Revert formatter
* Move QK norm stack to private function so it's easier to read
* refactor stablelm graph builder to support 1.6, 3b and 12b more efficiently
* Proper check for None type for new_name to avoid crash; formatting; revert change to base class `write_tensors()`
* Format
* Formatting
* format
Co-authored-by: compilade <redacted>
* Fix incorrect check for K norm
* space after commas; Keep indentation multiple of 4 spaces
* Flake8 format
* Removed unnecessary conditional branches
* Removed unused comment
* Fixed incorrect tensor passing
* Format
---------
Co-authored-by: compilade <redacted>
Shijie [Tue, 16 Apr 2024 15:40:48 +0000 (23:40 +0800)]
llama : add qwen2moe (#6074)
* support qwen2moe
* fix-review
* metal : support unary ops for nelements % 4 != 0
* metal : require contiguousness for float4 unary kernels
* metal : require contiguousness for float4 unary kernels (cont)
* fix-review
* names : for brevity "SHARED_EXP" -> "SHEXP"
* llama : reuse build_moe_ffn()
* llama : add model type name
---------
Co-authored-by: Georgi Gerganov <redacted>
Daniel Bevenius [Tue, 16 Apr 2024 06:34:06 +0000 (08:34 +0200)]
gritlm : add --outdir option to hf.sh script (#6699)
This commit updates the hf.sh script usage to include the --outdir option
and specifies the models directory as the output directory.
The motivation for this is to avoid cluttering the root directory with
model files.
Signed-off-by: Daniel Bevenius <redacted>
Georgi Gerganov [Tue, 16 Apr 2024 06:28:33 +0000 (09:28 +0300)]
perplexity : require positive --ctx-size arg (#6695)
Daniel Bevenius [Tue, 16 Apr 2024 06:13:13 +0000 (08:13 +0200)]
gguf : add special tokens metadata for FIM/Infill (#6689)
This commit adds special token metadata for Fill-In-the-Middle
(FIM)/Infill to the GGUF model.
The motivation for this is that currently there is support for CodeLlama
but other models exist now like CodeGemma, but the different models use
different token ids for the special tokens and this commit allows for
supporting multiple models.
Signed-off-by: Daniel Bevenius <redacted>
Olivier Chafik [Mon, 15 Apr 2024 17:35:21 +0000 (18:35 +0100)]
`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
compilade [Mon, 15 Apr 2024 12:56:55 +0000 (08:56 -0400)]
llama : fix restoring the number of outputs from state files (#6687)
Pierrick Hymbert [Mon, 15 Apr 2024 12:18:47 +0000 (14:18 +0200)]
server : revert "minor layout improvements" (#6684)
This reverts commit
b3a96f27f065a828f08c5d89ff60aab5361188fe .
Steven Prichard [Mon, 15 Apr 2024 10:14:46 +0000 (05:14 -0500)]
swift : linux support (#6590)
- Package.swift now supports conditional compilation based on OS
- Allows for package to be used by SPM on Non-Apple platforms
Co-authored-by: Steven Prichard <redacted>
Neo Zhang Jianyu [Mon, 15 Apr 2024 09:12:26 +0000 (17:12 +0800)]
fix mul_mat_id() for new input, make the ut pass (#6682)
David Renshaw [Sun, 14 Apr 2024 19:24:15 +0000 (15:24 -0400)]
llama : add missing kv clear in llama_beam_search (#6664)
Chao Jiang [Sun, 14 Apr 2024 16:16:34 +0000 (00:16 +0800)]
Add Command R chat template (#6650)
* Add chat template for command-r model series
* Fix indentation
* Add chat template test for command-r models and update the implementation to trim whitespaces
* Remove debug print
Georgi Gerganov [Sun, 14 Apr 2024 13:55:30 +0000 (16:55 +0300)]
flake.lock: Update (#6669)
Dave [Sun, 14 Apr 2024 11:14:19 +0000 (07:14 -0400)]
Added support for GGML_OP_CLAMP in Metal (#6662)
* Added support for GGML_OP_CLAMP in Metal
* Corrected size
---------
Co-authored-by: dave-fl <redacted>
Sigbjørn Skjæret [Sun, 14 Apr 2024 11:12:59 +0000 (13:12 +0200)]
Fix --split-max-size (#6655)
* Fix --split-max-size
Byte size calculation was done on int and overflowed.
* add tests.sh
* add examples test scripts to ci run
Will autodiscover examples/*/tests.sh scripts and run them.
* move WORK_PATH to a subdirectory
* clean up before and after test
* explicitly define which scripts to run
* add --split-max-size to readme
Jaemin Son [Sun, 14 Apr 2024 11:12:36 +0000 (20:12 +0900)]
[bug fix] convert github repository_owner to lowercase (#6673)
James A Capozzoli [Sun, 14 Apr 2024 08:40:18 +0000 (04:40 -0400)]
convert : enable the `--use-temp-file` cli flag (#6645)
Neo Zhang Jianyu [Sun, 14 Apr 2024 02:42:29 +0000 (10:42 +0800)]
fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
* disable mmap to fix memcpy crash, add missed cmd in guide, fix softmax
* refactor to disable mmap for SYCL backend
* fix compile error in other os
* refactor the solution, use host buf to fix it, instead of disable mmap
* keep to support mmap()
* use host buff to reduce malloc times
* revert to malloc/free solution, for threaad safe
Johannes Gäßler [Sat, 13 Apr 2024 22:21:55 +0000 (00:21 +0200)]
CUDA: fix matrix multiplication logic for tests (#6667)
Pierrick Hymbert [Sat, 13 Apr 2024 09:33:52 +0000 (11:33 +0200)]
model: support arch `DbrxForCausalLM` (#6515)
* model: dbrx convert to gguf
#6344
* llama: support dbrx
#6344
* doc: dbrx: add the model as supported
* scripts: get-wikitext-2 add unzip
* llama: increase maximum experts allowed
* llama: factorize moe graph implementation between grok, mixtral and dbrx
---------
Co-authored-by: Megha Agarwal <redacted>
Olivier Chafik [Fri, 12 Apr 2024 18:43:38 +0000 (19:43 +0100)]
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
* json: rename python schema converter to make import easier
* server: skip null json_schema / grammar fields
* json: deps management for primitive rules (+ allow null values)
* json: optimize repetitions for minItems/maxItems and regexps: `a{,3}` goes from `"a"? "a"? "a"?` (explosive combos) to `(a (a (a)?)?)?`
* grammars: add troubleshooting section to readme
* json: cap length of numbers to 15 digits before/after decimal point
(avoids infinite gen, e.g. "one third" -> `0.
333333333333 ...`)
* json: unify all repetition code (w/ or w/o sep)
* json: support string minLength/maxLength
* server+json: update server/README w/ result_format
* nits
* json: fix type error w/ python 3.8
* json: fix server/README (json_schema in /completion vs. result_format in /v1/chat/completions)
* json: simplify DOT `{"type": "string", "pattern": "^.$"}`
* json: remove recursion in opt_repetitions (avoids Python stack overflow)
* json: rm dead code
* json: rm useless assert & ggml.h import
slaren [Fri, 12 Apr 2024 16:13:20 +0000 (18:13 +0200)]
metal : unify mul_mv_id kernels (#6556)
Daniel Bevenius [Fri, 12 Apr 2024 12:11:46 +0000 (14:11 +0200)]
infill : add download instructions for model (#6626)
* infill : add download instructions for model
This commit adds instructions on how to download a CodeLlama model
using the `hf.sh` script. This will download the model and place it
in the `models` directory which is the same model use later by the
infill example.
Signed-off-by: Daniel Bevenius <redacted>
* squash! infill : add download instructions for model
Clarify the reason for using CodeLlama.
Signed-off-by: Daniel Bevenius <redacted>
---------
Signed-off-by: Daniel Bevenius <redacted>
Pierrick Hymbert [Fri, 12 Apr 2024 11:49:21 +0000 (13:49 +0200)]
server : coherent log output for KV cache full (#6637)
jiez [Fri, 12 Apr 2024 10:45:06 +0000 (18:45 +0800)]
llama : add gguf_remove_key + remove split meta during quantize (#6591)
* Remove split metadata when quantize model shards
* Find metadata key by enum
* Correct loop range for gguf_remove_key and code format
* Free kv memory
---------
Co-authored-by: z5269887 <redacted>
Rene Leonhardt [Fri, 12 Apr 2024 08:52:36 +0000 (10:52 +0200)]
chore: Fix markdown warnings (#6625)
Georgi Gerganov [Fri, 12 Apr 2024 08:49:58 +0000 (11:49 +0300)]
imatrix : remove invalid assert (#6632)
MasterYi1024 [Fri, 12 Apr 2024 08:28:12 +0000 (16:28 +0800)]
Correct free memory and total memory. (#6630)
Co-authored-by: MasterYi <redacted>
Pierrick Hymbert [Fri, 12 Apr 2024 08:26:47 +0000 (10:26 +0200)]
eval-callback: use ggml_op_desc to pretty print unary operator name (#6631)
Georgi Gerganov [Fri, 12 Apr 2024 08:15:05 +0000 (11:15 +0300)]
ci : disable Metal for macOS-latest-cmake-x64 (#6628)
Clint Herron [Fri, 12 Apr 2024 01:44:50 +0000 (21:44 -0400)]
Optimization: eliminate addition of redundant stacks when advancing grammar. (#6616)
Clint Herron [Thu, 11 Apr 2024 21:44:48 +0000 (17:44 -0400)]
As suggested by @slaren, disabling Metal for test to fix CI build on OSX from #6576 (#6619)
Nikolas [Thu, 11 Apr 2024 19:56:29 +0000 (21:56 +0200)]
Refactor Error Handling for CUDA (#6575)
* Refactor Error Handling for CUDA
Add guidance for setting CUDA_DOCKER_ARCH to match GPU compute capability for CUDA versions < 11.7. Include link to NVIDIA's CUDA GPUs documentation for compute capability reference.
* Update Makefile
Improved wording
Co-authored-by: Johannes Gäßler <redacted>
---------
Co-authored-by: Johannes Gäßler <redacted>
Olivier Chafik [Thu, 11 Apr 2024 18:47:34 +0000 (19:47 +0100)]
grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses) (#6609)
* grammars: reserve rejects & next candidates
* grammars: reuse new_stacks
* grammars: fix missing sig change in llama.h
* grammars: fix test (api changed)
* grammars: update gbnf-validator.cpp
* grammars: simpler syntax (no swap)
Hugo Roussel [Thu, 11 Apr 2024 17:52:21 +0000 (19:52 +0200)]
ci: download artifacts to release directory (#6612)
When action download-artifact was updated to v4, the default download path changed.
This fix binaries not being uploaded to releases.
Daniel Bevenius [Thu, 11 Apr 2024 13:22:47 +0000 (15:22 +0200)]
scripts : add --outdir option to hf.sh (#6600)
* scripts : add --outdir option to hf.sh
This commit adds an option to the hf.sh script that allows the user to
specify an output directory for the downloaded file.
The motivation for this changes is that examples that use the hf.sh
script to download models from huggingface can now specify the output
directory, perhaps to the `models` directory to keep them in one place
and not clutter the root directory.
Signed-off-by: Daniel Bevenius <redacted>
* squash! scripts : add --outdir option to hf.sh
Fix format of the --outdir option in the usage message.
Signed-off-by: Daniel Bevenius <redacted>
---------
Signed-off-by: Daniel Bevenius <redacted>
Pierrick Hymbert [Thu, 11 Apr 2024 12:51:07 +0000 (14:51 +0200)]
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 <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Daniel Bevenius [Wed, 10 Apr 2024 18:16:48 +0000 (20:16 +0200)]
gguf : add option to not check tensor data (#6582)
This commit adds an option to the gguf example to not check the tensor
data.
The motivation for this is that it can be nice to use the gguf tool to
read other .gguf files that were not created by the gguf tool.
Signed-off-by: Daniel Bevenius <redacted>
Ralph Soika [Wed, 10 Apr 2024 17:18:25 +0000 (19:18 +0200)]
minor layout improvements (#6572)
* minor layout improvements
* added missing file, run deps.sh locally
slaren [Wed, 10 Apr 2024 15:24:14 +0000 (17:24 +0200)]
llama : add model types for mixtral (#6589)
slaren [Wed, 10 Apr 2024 13:23:12 +0000 (15:23 +0200)]
convert.py : add consolidated.safetensors for mixtral 8x22b (#6587)
Pierrick Hymbert [Wed, 10 Apr 2024 06:58:48 +0000 (08:58 +0200)]
docs : how to add a model (#6565)
* docs: how to add a model
* docs: model: typo and docs
* docs: model: add prevision on RoPE
* docs: model: rephrasing README.md
* docs: model: rephrasing README.md
* docs: model: README.md fix trailing spaces
* docs : some fixes
* Update README.md
---------
Co-authored-by: Georgi Gerganov <redacted>
Artem Zinnatullin [Wed, 10 Apr 2024 06:49:12 +0000 (00:49 -0600)]
readme : fix ROCm link (#6579)
sjxx [Wed, 10 Apr 2024 06:34:00 +0000 (14:34 +0800)]
readme : update UI list (#6560)
Jiří Sejkora [Tue, 9 Apr 2024 22:23:02 +0000 (00:23 +0200)]
readme: fix typo in amdgpu target name (#6573)
Jared Van Bortel [Tue, 9 Apr 2024 17:44:08 +0000 (13:44 -0400)]
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
Georgi Gerganov [Tue, 9 Apr 2024 17:29:06 +0000 (20:29 +0300)]
sync : ggml
Ed Lee [Tue, 9 Apr 2024 08:31:47 +0000 (01:31 -0700)]
server : detect search query to start webchat (#6554)
Carolinabanana [Tue, 9 Apr 2024 08:16:13 +0000 (09:16 +0100)]
llama : add Command R Plus support (#6491)
* Add Command R Plus GGUF
* Add Command R Plus GGUF
* Loading works up to LayerNorm2D
* Export new tensors in 1D so they are not quantized.
* Fix embedding layer based on Noeda's example
* Whitespace
* Add line
* Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)
* dranger003: Fix block index overflow in CUDA dequantizing.
* Reverted blocked multiplication code as it still has issues and could affect other Llama arches
* export norms as f32
* fix overflow issues during quant and other cleanup
* Type convention
Co-authored-by: Georgi Gerganov <redacted>
* dranger003: Fix more int overflow during quant.
---------
Co-authored-by: S <redacted>
Co-authored-by: S <redacted>
Co-authored-by: slaren <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Georgi Gerganov [Tue, 9 Apr 2024 06:23:19 +0000 (09:23 +0300)]
license : update copyright notice + add AUTHORS (#6405)
* license : add AUTHORS
* authors : update
* scipts : add LICENSE and gen-authors.sh to sync
Georgi Gerganov [Mon, 8 Apr 2024 19:25:49 +0000 (22:25 +0300)]
llama : fix attention layer count sanity check (#6550)
* llama : fix attention layer count sanity check
* llama : fix parentheses in attention layer count sanity check
There was otherwise a warning when compiling.
---------
Co-authored-by: Francis Couture-Harpin <redacted>
kunnis [Mon, 8 Apr 2024 15:44:19 +0000 (10:44 -0500)]
Comment explaining a decision (#6531)
Georgi Gerganov [Mon, 8 Apr 2024 13:23:01 +0000 (16:23 +0300)]
quantize : fix precedence of cli args (#6541)
Rick G [Mon, 8 Apr 2024 13:02:30 +0000 (06:02 -0700)]
llama : support negative ith in llama_get_ API (#6519)
* llama_sampling_sample with default args is more naively usable
* Batches populated by either llama_batch_get_one or llama_batch_add work with default args
* Previously get_one could use the default argument
* Previously add should usually have used the last index where logits[idx] == true
* This hopefully encourages the use of llama_batch_add
* By giving expected results when using default arguments.
* Adds "negative indexing" feature to llama_get_logits_ith and llama_get_embeddings_ith
* Believed to work with any currently well behaved program
* Default arg now works for both cases (previously would give strange results for add case)
* Any non-negative number is unaffected and behaves as previously
* Negative arguments were previously invalid.
* Implemented as a special case of indexing as suggested by @compilade in https://github.com/ggerganov/llama.cpp/pull/6519
* Fixed mismatch type errors
* cited in macOS CI tests
* Missed in original updates based on PR feedback in https://github.com/ggerganov/llama.cpp/pull/6519
Jan Boon [Mon, 8 Apr 2024 12:43:30 +0000 (20:43 +0800)]
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 <redacted>
Co-authored-by: Georgi Gerganov <redacted>
Abhilash Majumder [Mon, 8 Apr 2024 08:26:01 +0000 (13:56 +0530)]
remove row=1 cond (#6532)
Firat [Mon, 8 Apr 2024 07:48:29 +0000 (00:48 -0700)]
Adding KodiBot to UI list (#6535)
KodiBot is free and open source ai chat app released under the GNU General Public License.
Mark Fairbairn [Sun, 7 Apr 2024 18:52:19 +0000 (19:52 +0100)]
Change Windows AMD example to release build to make inference much faster. (#6525)
Georgi Gerganov [Sun, 7 Apr 2024 18:25:30 +0000 (21:25 +0300)]
flake.lock: Update (#6517)
Flake lock file updates:
• Updated input 'flake-parts':
'github:hercules-ci/flake-parts/
f7b3c975cf067e56e7cda6cb098ebe3fb4d74ca2 ' (2024-03-01)
→ 'github:hercules-ci/flake-parts/
9126214d0a59633752a136528f5f3b9aa8565b7d ' (2024-04-01)
• Updated input 'flake-parts/nixpkgs-lib':
'github:NixOS/nixpkgs/
1536926ef5621b09bba54035ae2bb6d806d72ac8 ?dir=lib' (2024-02-29)
→ 'github:NixOS/nixpkgs/
d8fe5e6c92d0d190646fb9f1056741a229980089 ?dir=lib' (2024-03-29)
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/
d8fe5e6c92d0d190646fb9f1056741a229980089 ' (2024-03-29)
→ 'github:NixOS/nixpkgs/
fd281bd6b7d3e32ddfa399853946f782553163b5 ' (2024-04-03)
Co-authored-by: github-actions[bot] <redacted>
DAN™ [Sun, 7 Apr 2024 17:33:59 +0000 (13:33 -0400)]
Add GritLM as supported models. (#6513)
Georgi Gerganov [Sun, 7 Apr 2024 14:05:51 +0000 (17:05 +0300)]
sync : ggml
Slava Primenko [Thu, 4 Apr 2024 12:49:24 +0000 (14:49 +0200)]
ggml: bypass code incompatible with CUDA < 11.1 (whisper/2020)
`cudaHostRegisterReadOnly` parameter was only introduced in CUDA 11.1
See this issue for more details:
https://github.com/ggerganov/examples/whisper/whisper.cpp/issues/2007
Georgi Gerganov [Sun, 7 Apr 2024 13:08:12 +0000 (16:08 +0300)]
scripts : sync ggml-cuda folder
limitedAtonement [Sun, 7 Apr 2024 11:05:40 +0000 (07:05 -0400)]
Run make to build the project (#6457)
Neo Zhang Jianyu [Sun, 7 Apr 2024 02:55:59 +0000 (10:55 +0800)]
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (#6521)
Georgi Gerganov [Sat, 6 Apr 2024 14:43:15 +0000 (17:43 +0300)]
sync : ggml
Daniel Bevenius [Wed, 3 Apr 2024 20:57:20 +0000 (22:57 +0200)]
backend : fix typo in scheduler documentation (ggml/781)
Signed-off-by: Daniel Bevenius <redacted>
Clint Herron [Sat, 6 Apr 2024 14:31:33 +0000 (10:31 -0400)]
Tests: Added integration tests for GBNF parser (#6472)
* Added integration tests for GBNF parser to validate correctness of parsing, as well as correctness of string matching. Intended for use to pin behavior while working on performance improvements.
* Fixing whitespace errors and cleaning error message alert to be clearer.
* Removing hacky include to llama.cpp from grammar integration test now that needed functions are available via internal API.
* Comment cleanup.
* Reorganizing tests for readability.
* Cleaning up debug message to make a bit more sense.
Pierrick Hymbert [Sat, 6 Apr 2024 03:40:47 +0000 (05:40 +0200)]
ci: bench: support sse and fix prompt processing time / server: add tokens usage in stream OAI response (#6495)
* ci: bench: support sse and fix prompt processing time
server: add tokens usage in stream mode
* ci: bench: README.md EOL
* ci: bench: remove total pp and tg as it is not accurate
* ci: bench: fix case when there is no token generated
* ci: bench: change to the 95 percentile for pp and tg as it is closer to what the server exports in metrics
* ci: bench: fix finish reason rate
Brian [Fri, 5 Apr 2024 18:41:38 +0000 (05:41 +1100)]
gguf.py : add licence and version to gguf writer (#6504)
Hoang Nguyen [Fri, 5 Apr 2024 18:39:43 +0000 (11:39 -0700)]
readme : update UI list (#6503)
* Add MindMac to UI list
* Update proprietary description
Co-authored-by: slaren <redacted>
---------
Co-authored-by: slaren <redacted>