| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 سال پیش |
|
ggml-cann
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 سال پیش |
|
ggml-cpu
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 سال پیش |
|
ggml-cuda
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 سال پیش |
|
ggml-hip
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 سال پیش |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 سال پیش |
|
ggml-metal
|
5e3b08d606
ggml : do not install metal source when embed library (ggml/1054)
|
1 سال پیش |
|
ggml-musa
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
1 سال پیش |
|
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 سال پیش |
|
ggml-rpc
|
a4dd490069
rpc : code cleanup (#11107)
|
1 سال پیش |
|
ggml-sycl
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 سال پیش |
|
ggml-vulkan
|
c3f9d25706
Vulkan: Fix float16 use on devices without float16 support + fix subgroup_size_control validation error (#11161)
|
1 سال پیش |
|
CMakeLists.txt
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 سال پیش |
|
ggml-alloc.c
|
130d0c90bd
ggml : remove return from ggml_gallocr_allocate_node (ggml/1048)
|
1 سال پیش |
|
ggml-backend-impl.h
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 سال پیش |
|
ggml-backend-reg.cpp
|
c792dcf488
ggml : allow loading backend with env variable (ggml/1059)
|
1 سال پیش |
|
ggml-backend.cpp
|
017cc5f446
ggml-backend : only offload from host buffers (fix) (#11124)
|
1 سال پیش |
|
ggml-common.h
|
750cb3e246
CUDA: rename macros to avoid conflicts with WinAPI (#10736)
|
1 سال پیش |
|
ggml-impl.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 سال پیش |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
1 سال پیش |
|
ggml-quants.c
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 سال پیش |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 سال پیش |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 سال پیش |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 سال پیش |
|
ggml.c
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 سال پیش |
|
gguf.cpp
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 سال پیش |
0cc4m
c3f9d25706
Vulkan: Fix float16 use on devices without float16 support + fix subgroup_size_control validation error (#11161)