| .. |
|
ggml-cuda
|
b078c619aa
cuda : suppress 'noreturn' warn in no_device_code (#8414)
|
1 年之前 |
|
ggml-sycl
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 年之前 |
|
kompute @ 4565194ed7
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
kompute-shaders
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
llamafile
|
6b2a849d1f
ggml : move sgemm sources to llamafile subfolder (#8394)
|
1 年之前 |
|
vulkan-shaders
|
bda62d7999
Vulkan MMQ Fix (#8479)
|
1 年之前 |
|
CMakeLists.txt
|
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515)
|
1 年之前 |
|
ggml-aarch64.c
|
8fac431b06
ggml : suppress unknown pragma 'GCC' on windows (#8460)
|
1 年之前 |
|
ggml-aarch64.h
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 年之前 |
|
ggml-alloc.c
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
ggml-backend-impl.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
ggml-backend.c
|
b549a1bbef
[SYCL] fix the mul_mat_id ut issues (#8427)
|
1 年之前 |
|
ggml-blas.cpp
|
368645698a
ggml : add NVPL BLAS support (#8329) (#8425)
|
1 年之前 |
|
ggml-common.h
|
0f1a39f343
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)
|
1 年之前 |
|
ggml-cuda.cu
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 年之前 |
|
ggml-impl.h
|
0f1a39f343
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)
|
1 年之前 |
|
ggml-kompute.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
ggml-metal.m
|
c917b67f06
metal : template-ify some of the kernels (#8447)
|
1 年之前 |
|
ggml-metal.metal
|
c917b67f06
metal : template-ify some of the kernels (#8447)
|
1 年之前 |
|
ggml-quants.c
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 年之前 |
|
ggml-quants.h
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 年之前 |
|
ggml-rpc.cpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 年之前 |
|
ggml-sycl.cpp
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 年之前 |
|
ggml-vulkan.cpp
|
bda62d7999
Vulkan MMQ Fix (#8479)
|
1 年之前 |
|
ggml.c
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 年之前 |
Johannes Gäßler
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515)