| .. |
|
ggml-blas
|
d337252acf
cmake : Fix broken CMake error messages (ggml/1252)
|
hai 8 meses |
|
ggml-cann
|
e21d2d4ae2
CANN: Simplify the environment variable setting(#13104)
|
hai 7 meses |
|
ggml-cpu
|
b7ce1ad1e3
ggml : fix weak alias win32 (whisper/0)
|
hai 7 meses |
|
ggml-cuda
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
hai 7 meses |
|
ggml-hip
|
84778e9770
CUDA/HIP: Share the same unified memory allocation logic. (#12934)
|
hai 9 meses |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
hai 1 ano |
|
ggml-metal
|
1f63e75f3b
metal : use less stack memory in FA kernel (#14088)
|
hai 7 meses |
|
ggml-musa
|
33983057d0
musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)
|
hai 8 meses |
|
ggml-opencl
|
4c763c8d1b
opencl: add `mul_mv_id_q4_0_f32_8x_flat` (#14003)
|
hai 7 meses |
|
ggml-rpc
|
2bb0467043
rpc : nicer error messages for RPC server crash (#14076)
|
hai 7 meses |
|
ggml-sycl
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
hai 7 meses |
|
ggml-vulkan
|
bd248d4dc7
vulkan: Better thread-safety for command pools/buffers (#14116)
|
hai 7 meses |
|
CMakeLists.txt
|
1a3b5e80f7
Add in-build ggml::ggml ALIAS library (ggml/1260)
|
hai 7 meses |
|
ggml-alloc.c
|
f057808ffa
ggml: Don't assert fail when tensor data changes (#13222)
|
hai 9 meses |
|
ggml-backend-impl.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
hai 11 meses |
|
ggml-backend-reg.cpp
|
ba7654380a
ggml-backend : fix backend search path (#12330)
|
hai 10 meses |
|
ggml-backend.cpp
|
b47ab7b8e9
sched : avoid changing cur_copy when a graph is already allocated (#13922)
|
hai 8 meses |
|
ggml-common.h
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
hai 7 meses |
|
ggml-impl.h
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
hai 8 meses |
|
ggml-opt.cpp
|
6c35981a64
mnist: fix segmentation fault (ggml/1227)
|
hai 8 meses |
|
ggml-quants.c
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
hai 7 meses |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
hai 1 ano |
|
ggml.c
|
a7b8d35f78
sync : whisper.cpp (ggml/1250)
|
hai 8 meses |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
hai 8 meses |
|
gguf.cpp
|
7675c555a1
gguf: fix failure on version == 0 (#13956)
|
hai 8 meses |
Jeff Bolz
bd248d4dc7
vulkan: Better thread-safety for command pools/buffers (#14116)