c83ad6d01e
ggml-backend : add device and backend reg interfaces ( #9707 )
...
Co-authored-by: Johannes Gäßler <johannesg@5d6.de >
2024-10-03 01:49:47 +02:00
6f1d9d71f4
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS ( #9641 )
...
* Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS
* Set ROCM_DOCKER_ARCH as string due it incorrectly build and cause OOM exit code
2024-09-30 20:57:12 +02:00
511636df0c
ci : reduce severity of unused Pyright ignore comments ( #9697 )
2024-09-30 14:13:16 -04:00
95bc82fbc0
[SYCL] add missed dll file in package ( #9577 )
...
* update oneapi to 2024.2
* use 2024.1
---------
Co-authored-by: arthw <14088817+arthw@users.noreply.github.com >
2024-09-26 17:38:31 +08:00
ea9c32be71
ci : fix docker build number and tag name ( #9638 )
...
* ci : fix docker build number and tag name
* fine-grant permissions
2024-09-25 17:26:01 +02:00
e948a7da7a
CI: Provide prebuilt windows binary for hip ( #9467 )
2024-09-21 02:39:41 +02:00
6262d13e0b
common : reimplement logging ( #9418 )
...
https://github.com/ggerganov/llama.cpp/pull/9418
2024-09-15 20:46:12 +03:00
78203641fe
server : Add option to return token pieces in /tokenize endpoint ( #9108 )
...
* server : added with_pieces functionality to /tokenize endpoint
* server : Add tokenize with pieces tests to server.feature
* Handle case if tokenizer splits along utf8 continuation bytes
* Add example of token splitting
* Remove trailing ws
* Fix trailing ws
* Maybe fix ci
* maybe this fix windows ci?
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2024-09-12 22:30:11 +02:00
4dc4f5f14a
ci : update HIP SDK to 24.Q3 (ROCm 6.1) ( #9329 )
2024-09-12 14:28:43 +03:00
3c26a1644d
ci : bump actions/checkout to v4 ( #9377 )
2024-09-12 14:27:45 +03:00
6c89eb0b47
ci : disable rocm image creation ( #9340 )
2024-09-07 10:48:54 +03:00
32b2ec88bc
Update build.yml ( #9184 )
...
build rpc-server for windows cuda
2024-09-06 00:34:36 +02:00
9fe94ccac9
docker : build images only once ( #9225 )
2024-08-28 17:28:00 +02:00
d5492f0525
ci : disable bench workflow ( #9010 )
2024-08-15 10:11:11 +03:00
fc4ca27b25
ci : fix github workflow vulnerable to script injection ( #9008 )
...
Signed-off-by: Diogo Teles Sant'Anna <diogoteles@google.com >
2024-08-12 19:28:23 +03:00
1f67436c5e
ci : enable RPC in all of the released builds ( #9006 )
...
ref: #8912
2024-08-12 19:17:03 +03:00
d3ae0ee8d7
py : fix requirements check '==' -> '~=' ( #8982 )
...
* py : fix requirements check '==' -> '~='
* cont : fix the fix
* ci : run on all requirements.txt
2024-08-12 11:02:01 +03:00
03adb90dc6
prompt command done
2024-08-07 20:52:28 +08:00
c7108742f4
fix typo
2024-08-06 17:24:58 +08:00
0d534d810f
Mac builds ( #1037 )
...
* OSX attempt 1
* OSX Pyinstaller
* Update kcpp-build-release-osx.yaml
* Update kcpp-build-release-osx.yaml
* Update kcpp-build-release-osx.yaml
* Add .metal file
* Update kcpp-build-release-osx.yaml
* Polish Mac
(cherry picked from commit 52cc0daa1b
2024-08-06 17:11:19 +08:00
6eeaeba126
cmake: use 1 more thread for non-ggml in CI ( #8740 )
2024-07-28 22:32:44 +02:00
a84f7c5d81
revert num old cpu for ci
2024-07-25 13:24:34 +08:00
e28c42d7f7
adjusted layer estimation
2024-07-24 21:54:49 +08:00
44ef87f14c
update lite, try fix ci
2024-07-24 16:31:34 +08:00
69c487f4ed
CUDA: MMQ code deduplication + iquant support ( #8495 )
...
* CUDA: MMQ code deduplication + iquant support
* 1 less parallel job for CI build
2024-07-20 22:25:26 +02:00
8412946b9f
fix oldcpu build avx1
2024-07-15 23:42:22 +08:00
21179d675b
try ci for avx1, up ver (+2 squashed commit)
...
Squashed commit:
[74150175] up version
[97b6163c] try ci for avx1 linux
2024-07-15 23:07:07 +08:00
1a6855f597
Merge branch 'concedo_experimental' into concedo
2024-07-15 00:02:50 +08:00
17eb6aa8a9
vulkan : cmake integration ( #8119 )
...
* Add Vulkan to CMake pkg
* Add Sycl to CMake pkg
* Add OpenMP to CMake pkg
* Split generated shader file into separate translation unit
* Add CMake target for Vulkan shaders
* Update README.md
* Add make target for Vulkan shaders
* Use pkg-config to locate vulkan library
* Add vulkan SDK dep to ubuntu-22-cmake-vulkan workflow
* Clean up tabs
* Move sudo to apt-key invocation
* Forward GGML_EXTRA_LIBS to CMake config pkg
* Update vulkan obj file paths
* Add shaderc to nix pkg
* Add python3 to Vulkan nix build
* Link against ggml in cmake pkg
* Remove Python dependency from Vulkan build
* code review changes
* Remove trailing newline
* Add cflags from pkg-config to fix w64devkit build
* Update README.md
* Remove trailing whitespace
* Update README.md
* Remove trailing whitespace
* Fix doc heading
* Make glslc required Vulkan component
* remove clblast from nix pkg
2024-07-13 18:12:39 +02:00
2cad736260
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/nix/package.nix
# .github/labeler.yml
# .gitignore
# CMakeLists.txt
# Makefile
# Package.swift
# README.md
# ci/run.sh
# docs/build.md
# examples/CMakeLists.txt
# flake.lock
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# grammars/README.md
# requirements/requirements-convert_hf_to_gguf.txt
# requirements/requirements-convert_hf_to_gguf_update.txt
# scripts/check-requirements.sh
# scripts/compare-llama-bench.py
# scripts/gen-unicode-data.py
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# scripts/sync-ggml.sh
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
# tests/test-tokenizer-random.py
2024-07-11 16:36:16 +08:00
cc133401db
Update issue templates ( #986 )
2024-07-10 11:36:00 +08:00
a130eccef4
labeler : updated sycl to match docs and code refactor ( #8373 )
2024-07-08 22:35:17 +02:00
3fd62a6b1c
py : type-check all Python scripts with Pyright ( #8341 )
...
* py : type-check all Python scripts with Pyright
* server-tests : use trailing slash in openai base_url
* server-tests : add more type annotations
* server-tests : strip "chat" from base_url in oai_chat_completions
* server-tests : model metadata is a dict
* ci : disable pip cache in type-check workflow
The cache is not shared between branches, and it's 250MB in size,
so it would become quite a big part of the 10GB cache limit of the repo.
* py : fix new type errors from master branch
* tests : fix test-tokenizer-random.py
Apparently, gcc applies optimisations even when pre-processing,
which confuses pycparser.
* ci : only show warnings and errors in python type-check
The "information" level otherwise has entries
from 'examples/pydantic_models_to_grammar.py',
which could be confusing for someone trying to figure out what failed,
considering that these messages can safely be ignored
even though they look like errors.
2024-07-07 15:04:39 -04:00
ecec9fb478
add target for oldcpu cuda
...
(cherry picked from commit 572aba8e9c
2024-07-06 00:40:23 +08:00
572aba8e9c
add target for oldcpu cuda
2024-07-06 00:37:01 +08:00
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. ( #8258 )
2024-07-02 12:18:10 -04:00
8748d8ac6f
json: attempt to skip slow tests when running under emulator ( #8189 )
2024-06-28 18:02:05 +01:00
558f44bf83
CI: fix release build (Ubuntu+Mac) ( #8170 )
...
* CI: fix release build (Ubuntu)
PR #8006 changes defaults to build shared libs. However, CI for releases
expects static builds.
* CI: fix release build (Mac)
---------
Co-authored-by: loonerin <loonerin@users.noreply.github.com >
2024-06-27 21:01:23 +02:00
ae5d0f4b89
ci : publish new docker images only when the files change ( #8142 )
2024-06-26 21:59:28 +02:00
f3f65429c4
llama : reorganize source code + improve CMake ( #8006 )
...
* scripts : update sync [no ci]
* files : relocate [no ci]
* ci : disable kompute build [no ci]
* cmake : fixes [no ci]
* server : fix mingw build
ggml-ci
* cmake : minor [no ci]
* cmake : link math library [no ci]
* cmake : build normal ggml library (not object library) [no ci]
* cmake : fix kompute build
ggml-ci
* make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE
ggml-ci
* move public backend headers to the public include directory (#8122 )
* move public backend headers to the public include directory
* nix test
* spm : fix metal header
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* scripts : fix sync paths [no ci]
* scripts : sync ggml-blas.h [no ci]
---------
Co-authored-by: slaren <slarengh@gmail.com >
2024-06-26 18:33:02 +03:00
c66371fbb0
cu toolkit ver
2024-06-26 12:41:05 +08:00
dd047b476c
disable docker CI on pull requests ( #8110 )
2024-06-25 19:20:06 +02:00
fdca385cd9
Give the CI builds a recognizable AVX1 name ( #937 )
2024-06-25 19:25:50 +08:00
8cb508d0d5
disable publishing the full-rocm docker image ( #8083 )
2024-06-24 08:36:11 +03:00
b6b9a8e606
fix CI failures ( #8066 )
...
* test-backend-ops : increase cpy max nmse
* server ci : disable thread sanitizer
2024-06-23 13:14:45 +02:00
9c77ec1d74
ggml : synchronize threads using barriers ( #7993 )
2024-06-19 15:04:15 +02:00
a04a953cab
codecov : remove ( #8004 )
2024-06-19 13:04:36 +03:00
967c1d8df5
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# Makefile
# README-sycl.md
# README.md
# flake.lock
# tests/test-backend-ops.cpp
2024-06-17 15:14:47 +08:00
c8a82194a8
github : update pr template
2024-06-16 10:46:51 +03:00
f8ec8877b7
ci : fix macos x86 build ( #7940 )
...
In order to use old `macos-latest` we should use `macos-12`
Potentially will fix: https://github.com/ggerganov/llama.cpp/issues/6975
2024-06-14 20:28:34 +03:00
Diego Devesa
serhii-nakon
compilade
Neo Zhang Jianyu
Xuan Son Nguyen
Huang Qi
Georgi Gerganov
Mathijs Henquet
Trivikram Kamat
awatuna
Diogo Teles Sant'Anna
Radoslav Gerganov
Concedo
henk717
Johannes Gäßler
bandoti
Alberto Cabrera Pérez
Clint Herron
Olivier Chafik
loonerin
olexiyb