| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
il y a 1 an |
|
ggml-cann
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-cpu
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-cuda
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-hip
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
il y a 1 an |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-metal
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-musa
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
il y a 1 an |
|
ggml-opencl
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
il y a 1 an |
|
ggml-rpc
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
il y a 1 an |
|
ggml-sycl
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
ggml-vulkan
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
|
CMakeLists.txt
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
il y a 1 an |
|
ggml-alloc.c
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
il y a 1 an |
|
ggml-backend-impl.h
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
il y a 1 an |
|
ggml-backend-reg.cpp
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
il y a 1 an |
|
ggml-backend.cpp
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
il y a 1 an |
|
ggml-common.h
|
750cb3e246
CUDA: rename macros to avoid conflicts with WinAPI (#10736)
|
il y a 1 an |
|
ggml-impl.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
il y a 1 an |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
il y a 1 an |
|
ggml-quants.c
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
il y a 1 an |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
il y a 1 an |
|
ggml.c
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
il y a 1 an |
HimariO
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)