COMMITS
/ CMakeLists.txt December 9, 2024
B
cmake : simplify msvc charsets (#10672)
Borislav Stanimirov committed
December 1, 2024
D
ggml : automatic selection of best CPU backend (#10606)
Diego Devesa committed
November 26, 2024
G
cmake : enable warnings in llama (#10474)
Georgi Gerganov committed
November 25, 2024
E
Introduce llama-run (#10291)
Eric Curtin committed
November 19, 2024
蕭
cmake: force MSVC compiler charset to utf-8 (#9989)
蕭澧邦 committed
November 14, 2024
D
ggml : build backends as libraries (#10256)
Diego Devesa committed
October 18, 2024
M
add amx kernel for gemm (#8998)
Ma Mingfei committed
October 9, 2024
D
cmake : do not build common library by default when standalone (#9804)
Diego Devesa committed
September 27, 2024
B
cmake : add option for common library (#9661)
Borislav Stanimirov committed
September 16, 2024
G
cmake : do not hide GGML options + rename option (#9465)
Georgi Gerganov committed
September 12, 2024
M
cmake : fix for builds without `GGML_CDEF_PUBLIC` (#9338)
Michael Podvitskiy committed
July 31, 2024
B
cmake : fix use of external ggml (#8787)
Borislav Stanimirov committed
July 17, 2024
H
[CANN] Add Ascend NPU backend (#6035)
hipudding committed
July 13, 2024
B
vulkan : cmake integration (#8119)
bandoti committed
July 9, 2024
J
make/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392)
Johannes Gäßler committed
B
cmake : allow external ggml (#8370)
Borislav Stanimirov committed
July 4, 2024
D
build: Export hf-to-gguf as snakecase
ditsuke committed
D
tests : add _CRT_SECURE_NO_WARNINGS for WIN32 (#8231)
Daniel Bevenius committed
July 2, 2024
D
chore: Fixup requirements and build
ditsuke committed
June 28, 2024
S
cmake : allow user to override default options (#8178)
slaren committed
June 27, 2024
S
cmake : fix deprecated option names not working (#8171)
slaren committed
June 26, 2024
S
G
llama : reorganize source code + improve CMake (#8006)
Georgi Gerganov committed
June 24, 2024
J
CUDA: use MMQ instead of cuBLAS by default (#8075)
Johannes Gäßler committed
S
ggml : remove ggml_task_type and GGML_PERF (#8017)
slaren committed
June 20, 2024
L
[SYCL] Fix windows build and inference (#8003)
luoyu-intel committed
June 16, 2024
0
Vulkan Shader Refactor, Memory Debugging Option (#7947)
0cc4m committed
June 15, 2024
M
[SYCL] remove global variables (#7710)
Meng, Hengyu committed
June 13, 2024
S
move BLAS to a separate backend (#6210)
slaren committed
June 10, 2024
J
cmake : fix CMake requirement for CUDA (#7821)
Jared Van Bortel committed
June 5, 2024
J
CUDA: refactor mmq, dmmv, mmvq (#7716)
Johannes Gäßler committed
June 4, 2024
G
ggml : remove OpenCL (#7735)
Georgi Gerganov committed
D
Improve hipBLAS support in CMake (#7696)
Daniele committed
June 3, 2024
M
ggml : use OpenMP as a thread pool (#7606)
Masaya, Kato committed
A
cmake : add pkg-config spec file for llama.cpp (#7702)
Andy Tai committed
W
kompute : implement op_getrows_f32 (#6403)
woachk committed
June 1, 2024
J
CUDA: quantized KV support for FA vec (#7527)
Johannes Gäßler committed
May 30, 2024
G
Move convert.py to examples/convert-legacy-llama.py (#7430)
Galunid committed
May 28, 2024
M
[SYCL] Align GEMM dispatch (#7566)
Meng, Hengyu committed
May 25, 2024
M
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
Masaya, Kato committed
May 23, 2024
G
ggml : drop support for QK_K=64 (#7473)
Georgi Gerganov committed
May 22, 2024
May 20, 2024
J
ggml : add loongarch lsx and lasx support (#6454)
junchao-loongson 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
E
cmake : fix typo in AMDGPU_TARGETS (#7356)
Engininja2 committed
May 17, 2024
G
ROCm: use native CMake HIP support (#5966)
Gavin Zhao committed
May 16, 2024
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