 Jag Chadha
|
527e57cfd8
build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (#3342)
|
2 年之前 |
 DAN™
|
99115f3fa6
cmake : fix build-info.h on MSVC (#3309)
|
2 年之前 |
 Johannes Gäßler
|
111163e246
CUDA: enable peer access between devices (#2470)
|
2 年之前 |
 Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 年之前 |
 Engininja2
|
7e50d34be6
cmake : fix building shared libs for clang (rocm) on windows (#3176)
|
2 年之前 |
 Andrei
|
76164fe2e6
cmake : fix llama.h location when built outside of root directory (#3179)
|
2 年之前 |
|
Andrei
|
769266a543
cmake : compile ggml-rocm with -fpic when building shared library (#3158)
|
2 年之前 |
 bandoti
|
990a5e226a
cmake : add relocatable Llama package (#2960)
|
2 年之前 |
 Tristan Ross
|
1b6c650d16
cmake : add a compiler flag check for FP16 format (#3086)
|
2 年之前 |
|
Johannes Gäßler
|
0a5eebb45d
CUDA: mul_mat_q RDNA2 tunings (#2910)
|
2 年之前 |
 Eric Sommerlade
|
b52b29ab9d
arm64 support for windows (#3007)
|
2 年之前 |
 Jhen-Jie Hong
|
1b0d09259e
cmake : support build for iOS/tvOS (#3116)
|
2 年之前 |
 Georgi Gerganov
|
b3e9852e47
sync : ggml (CUDA GLM RoPE + POSIX) (#3082)
|
2 年之前 |
 Przemysław Pawełczyk
|
cb6c44c5e0
build : do not use _GNU_SOURCE gratuitously (#2035)
|
2 年之前 |
 Kunshang Ji
|
7f412dab9c
enable CPU HBM (#2603)
|
2 年之前 |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
2 年之前 |
|
Cebtenzzre
|
9912b9efc8
build : add LLAMA_METAL_NDEBUG flag (#3033)
|
2 年之前 |
|
Georgi Gerganov
|
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
|
2 年之前 |
|
Cebtenzzre
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 年之前 |
|
Cebtenzzre
|
849408957c
tests : add a C compliance test (#2848)
|
2 年之前 |
|
Georgi Gerganov
|
3a007648f2
metal : add option to disable debug logs (close #2764)
|
2 年之前 |
 Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
2 年之前 |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 年之前 |
 Kolen Cheung
|
0919a0f73d
cmake : install ggml-meta.metal if LLAMA_METAL (#2449)
|
2 年之前 |
 Shouzheng Liu
|
bf83bff674
metal : matrix-matrix multiplication kernel (#2615)
|
2 年之前 |
|
Johannes Gäßler
|
f64d44a9b9
CUDA: Fixed OpenLLaMA 3b mmq, reduced compile time (#2590)
|
2 年之前 |
|
Johannes Gäßler
|
4f6b60c776
CUDA: Fix models with output size != 32000 (#2480)
|
2 年之前 |
|
Johannes Gäßler
|
b772bba42e
CUDA: fixed cmake F16 option (#2471)
|
2 年之前 |
|
Johannes Gäßler
|
0728c5a8b9
CUDA: mmq CLI option, fixed mmq build issues (#2453)
|
2 年之前 |
 slaren
|
a113689571
ggml : add graph tensor allocator (#2411)
|
2 年之前 |
