| .. |
|
ggml-alloc.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml-backend.h
|
a15ef8f8a0
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)
|
пре 1 година |
|
ggml-blas.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml-cann.h
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
пре 1 година |
|
ggml-cuda.h
|
e54c35e4fb
feat: Support Moore Threads GPU (#8383)
|
пре 1 година |
|
ggml-kompute.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml-metal.h
|
85fca8deb6
metal : add abort callback (ggml/905)
|
пре 1 година |
|
ggml-rpc.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml-sycl.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml-vulkan.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
пре 1 година |
|
ggml.h
|
e11bd856d5
CPU/CUDA: Gemma 2 FlashAttention support (#8542)
|
пре 1 година |
Johannes Gäßler
e11bd856d5
CPU/CUDA: Gemma 2 FlashAttention support (#8542)