| .. |
|
ggml-cann
|
ba1cf846ed
cann : fix doxy (ggml/0)
|
1 year ago |
|
ggml-cuda
|
c35e586ea5
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)
|
1 year ago |
|
ggml-sycl
|
5910ea9427
[SYCL] Fix DMMV dequantization (#9279)
|
1 year ago |
|
kompute @ 4565194ed7
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
kompute-shaders
|
06943a69f6
ggml : move rope type enum to ggml.h (#8949)
|
1 year ago |
|
llamafile
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
vulkan-shaders
|
8ebe8ddebd
Improve Vulkan shader build system (#9239)
|
1 year ago |
|
CMakeLists.txt
|
c35e586ea5
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)
|
1 year ago |
|
ggml-aarch64.c
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
ggml-aarch64.h
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 year ago |
|
ggml-alloc.c
|
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
|
1 year ago |
|
ggml-backend-impl.h
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml-backend.c
|
27609c49b9
ggml : fix trailing whitespace (#0)
|
1 year ago |
|
ggml-blas.cpp
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
1 year ago |
|
ggml-cann.cpp
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml-common.h
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
ggml-cpu-impl.h
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
ggml-cuda.cu
|
c35e586ea5
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)
|
1 year ago |
|
ggml-impl.h
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
ggml-kompute.cpp
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml-metal.m
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml-metal.metal
|
231cff5f6f
sync : ggml
|
1 year ago |
|
ggml-quants.c
|
23e0d70bac
ggml : move common CPU backend impl to new header (#9509)
|
1 year ago |
|
ggml-quants.h
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
ggml-rpc.cpp
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml-sycl.cpp
|
d13edb17ed
ggml : fix builds (#0)
|
1 year ago |
|
ggml-vulkan.cpp
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
ggml.c
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
R0CKSTAR
c35e586ea5
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)