| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-cann
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 year ago |
|
ggml-cpu
|
d2e518e9b4
ggml-cpu : fix ggml_graph_compute_thread did not terminate on abort. (ggml/1065)
|
11 months ago |
|
ggml-cuda
|
be5ef7963f
HIP: Supress transformation warning in softmax.cu
|
11 months ago |
|
ggml-hip
|
26771a1491
Hip: disable VMM on hip as it seams that it dosent work in some configurations (#11420)
|
1 year ago |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 year ago |
|
ggml-metal
|
acd38efee3
metal: Handle null returned from MTLCreateSystemDefaultDevice() (#11441)
|
11 months ago |
|
ggml-musa
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
1 year ago |
|
ggml-opencl
|
6e1531aca5
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON (#11013)
|
1 year ago |
|
ggml-rpc
|
6da5bec81c
rpc : better caching of the base buffer pointer (#11331)
|
1 year ago |
|
ggml-sycl
|
6e84b0ab8e
SYCL : SOFTMAX F16 mask support and other fixes (#11261)
|
11 months ago |
|
ggml-vulkan
|
66ee4f297c
vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)
|
11 months ago |
|
CMakeLists.txt
|
4bf3119d61
cmake : don't fail on `GGML_CPU=OFF` (#11457)
|
11 months ago |
|
ggml-alloc.c
|
9c8dcefe17
CUDA: backwards pass for misc. ops, add tests (#11257)
|
1 year ago |
|
ggml-backend-impl.h
|
667d72846c
rpc : early register backend devices (#11262)
|
1 year ago |
|
ggml-backend-reg.cpp
|
c792dcf488
ggml : allow loading backend with env variable (ggml/1059)
|
1 year ago |
|
ggml-backend.cpp
|
017cc5f446
ggml-backend : only offload from host buffers (fix) (#11124)
|
1 year ago |
|
ggml-common.h
|
750cb3e246
CUDA: rename macros to avoid conflicts with WinAPI (#10736)
|
1 year ago |
|
ggml-impl.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 year ago |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
1 year ago |
|
ggml-quants.c
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 year ago |
|
ggml.c
|
1a0e87d291
ggml : add option to not print stack on abort (ggml/1081)
|
11 months ago |
|
gguf.cpp
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
1 year ago |
Rémy Oudompheng
66ee4f297c
vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)