COMMITS
/ .github/workflows/build.yml December 8, 2024
D
llama : use cmake for swift build (#10525)
Diego Devesa committed
December 2, 2024
G
make : deprecate (#10514)
Georgi Gerganov committed
November 29, 2024
D
ggml : move AMX to the CPU backend (#10570)
Diego Devesa committed
November 28, 2024
D
ci : fix tag name in cuda and hip releases (#10566)
Diego Devesa committed
November 27, 2024
D
ci : faster CUDA toolkit installation method and use ccache (#10537)
Diego Devesa committed
November 26, 2024
D
ci : fix cuda releases (#10532)
Diego Devesa committed
N
restore the condistion to build & update pacakge when merge (#10507)
Neo Zhang Jianyu committed
D
ci : add ubuntu cuda build, build with one arch on windows (#10456)
Diego Devesa committed
November 25, 2024
N
[SYCL] Fix building Win package for oneAPI 2025.0 update (#10483)
Neo Zhang Jianyu committed
November 22, 2024
蕭
ci: Update oneAPI runtime dll packaging (#10428)
蕭澧邦 committed
November 15, 2024
R
ci: build test musa with cmake (#10298)
R0CKSTAR committed
R
sycl: Use syclcompat::dp4a (#10267)
Romain Biessy committed
November 14, 2024
D
ggml : build backends as libraries (#10256)
Diego Devesa committed
November 8, 2024
G
metal : opt-in compile flag for BF16 (#10218)
Georgi Gerganov committed
November 4, 2024
E
Q6_K AVX improvements (#10118)
Eve committed
October 4, 2024
X
ci : fine-grant permission (#9710)
Xuan Son Nguyen committed
September 30, 2024
S
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)
serhii-nakon committed
September 26, 2024
N
[SYCL] add missed dll file in package (#9577)
Neo Zhang Jianyu committed
September 21, 2024
H
CI: Provide prebuilt windows binary for hip (#9467)
Huang Qi committed
September 15, 2024
G
common : reimplement logging (#9418)
Georgi Gerganov committed
September 12, 2024
H
ci : update HIP SDK to 24.Q3 (ROCm 6.1) (#9329)
Huang Qi committed
T
ci : bump actions/checkout to v4 (#9377)
Trivikram Kamat committed
September 5, 2024
A
Update build.yml (#9184)
awatuna committed
August 12, 2024
R
ci : enable RPC in all of the released builds (#9006)
Radoslav Gerganov committed
July 28, 2024
J
cmake: use 1 more thread for non-ggml in CI (#8740)
Johannes Gäßler committed
July 20, 2024
J
CUDA: MMQ code deduplication + iquant support (#8495)
Johannes Gäßler committed
July 13, 2024
B
vulkan : cmake integration (#8119)
bandoti committed
June 28, 2024
O
json: attempt to skip slow tests when running under emulator (#8189)
Olivier Chafik committed
June 27, 2024
L
CI: fix release build (Ubuntu+Mac) (#8170)
loonerin committed
June 26, 2024
S
ci : publish new docker images only when the files change (#8142)
slaren committed
G
llama : reorganize source code + improve CMake (#8006)
Georgi Gerganov committed
June 14, 2024
O
ci : fix macos x86 build (#7940)
olexiyb committed
June 12, 2024
O
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
Olivier Chafik committed
June 11, 2024
S
fix CUDA CI by using a windows-2019 image (#7861)
slaren committed
June 4, 2024
G
ggml : remove OpenCL (#7735)
Georgi Gerganov committed
June 3, 2024
M
ggml : use OpenMP as a thread pool (#7606)
Masaya, Kato committed
May 19, 2024
S
llama : remove MPI backend (#7395)
slaren committed
May 18, 2024
G
ci : re-enable sanitizer runs (#7358)
Georgi Gerganov committed
May 17, 2024
G
ROCm: use native CMake HIP support (#5966)
Gavin Zhao committed
May 16, 2024
M
ci: fix bin/Release path for windows-arm64 builds (#7317)
Max Krasnyansky committed
M
Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)
Max Krasnyansky committed
May 14, 2024
R
ggml : add RPC backend (#6829)
Radoslav Gerganov committed
May 13, 2024
N
[SYCL] Add oneapi runtime dll files to win release package (#7241)
Neo Zhang committed
N
[SYCL] update CI with oneapi 2024.1 (#7235)
Neo Zhang committed
April 29, 2024
P
ci : add building in MSYS2 environments (Windows) (#6967)
Przemysław Pawełczyk committed
April 19, 2024
L
April 12, 2024
G
ci : disable Metal for macOS-latest-cmake-x64 (#6628)
Georgi Gerganov committed
April 11, 2024
H
ci: download artifacts to release directory (#6612)
Hugo Roussel committed
P
eval-callback: Example how to use eval callback for debugging (#6576)
Pierrick Hymbert committed
April 4, 2024
M
ci: exempt master branch workflows from getting cancelled (#6486)
Minsoo Cheong committed