| .. |
|
ggml-alloc.h
|
42c76d1358
Threadpool: take 2 (#8672)
|
hai 1 ano |
|
ggml-backend.h
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
hai 1 ano |
|
ggml-blas.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
ggml-cann.h
|
e6b7801bd1
cann: Add host buffer type for Ascend NPU (#9406)
|
hai 1 ano |
|
ggml-cuda.h
|
e54c35e4fb
feat: Support Moore Threads GPU (#8383)
|
hai 1 ano |
|
ggml-kompute.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
ggml-metal.h
|
85fca8deb6
metal : add abort callback (ggml/905)
|
hai 1 ano |
|
ggml-rpc.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
ggml-sycl.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
ggml-vulkan.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
ggml.h
|
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)
|
hai 1 ano |
Dan Johansson
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)