| .. |
|
ggml-cuda
|
8e558309dc
CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
|
1 year ago |
|
ggml-sycl
|
1f3e1b66e2
Enabled more data types for oneMKL gemm_batch (#8236)
|
1 year ago |
|
kompute @ 4565194ed7
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
kompute-shaders
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
vulkan-shaders
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
CMakeLists.txt
|
1d894a790e
cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
|
1 year ago |
|
ggml-alloc.c
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-backend-impl.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-backend.c
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-blas.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-common.h
|
cb5fad4c6c
CUDA: refactor and optimize IQ MMVQ (#8215)
|
1 year ago |
|
ggml-cuda.cu
|
0e0590adab
cuda : update supports_op for matrix multiplication (#8245)
|
1 year ago |
|
ggml-impl.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-kompute.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-metal.m
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-metal.metal
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 year ago |
|
ggml-quants.c
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-quants.h
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 year ago |
|
ggml-rpc.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml-sycl.cpp
|
1f3e1b66e2
Enabled more data types for oneMKL gemm_batch (#8236)
|
1 year ago |
|
ggml-vulkan-shaders.hpp
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 year ago |
|
ggml-vulkan.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
ggml.c
|
f8d6a23804
fix typo (#8267)
|
1 year ago |
|
sgemm.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
sgemm.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
Natsu
1d894a790e
cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)