| .. |
|
ggml-blas
|
d337252acf
cmake : Fix broken CMake error messages (ggml/1252)
|
7 月之前 |
|
ggml-cann
|
1e8659e65a
CANN: Add SOC TYPE printing in cmake configuration (#13837)
|
7 月之前 |
|
ggml-cpu
|
482548716f
releases : use dl backend for linux release, remove arm64 linux release (#13996)
|
7 月之前 |
|
ggml-cuda
|
0b4be4c435
CUDA: fix FTZ in FA for Gemma 3 (#13991)
|
7 月之前 |
|
ggml-hip
|
84778e9770
CUDA/HIP: Share the same unified memory allocation logic. (#12934)
|
9 月之前 |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 年之前 |
|
ggml-metal
|
ea394d7ab1
metal : use F32 accumulators in FA kernels (#13975)
|
7 月之前 |
|
ggml-musa
|
33983057d0
musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)
|
8 月之前 |
|
ggml-opencl
|
71e74a3ac9
opencl: add `backend_synchronize` (#13939)
|
7 月之前 |
|
ggml-rpc
|
b486ba05bf
rpc : add rpc_msg_set_tensor_hash_req (#13353)
|
8 月之前 |
|
ggml-sycl
|
663445b0de
sycl: quantize and reorder the input to q8_1 when reorder is enabled (#13826)
|
7 月之前 |
|
ggml-vulkan
|
669c13e0f6
vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs (#14001)
|
7 月之前 |
|
CMakeLists.txt
|
3a077146a4
llama : allow using mmap without PrefetchVirtualMemory, apply GGML_WIN_VER to llama.cpp sources (#14013)
|
7 月之前 |
|
ggml-alloc.c
|
f057808ffa
ggml: Don't assert fail when tensor data changes (#13222)
|
8 月之前 |
|
ggml-backend-impl.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 月之前 |
|
ggml-backend-reg.cpp
|
ba7654380a
ggml-backend : fix backend search path (#12330)
|
10 月之前 |
|
ggml-backend.cpp
|
b47ab7b8e9
sched : avoid changing cur_copy when a graph is already allocated (#13922)
|
7 月之前 |
|
ggml-common.h
|
492d7f1ff7
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (#12611)
|
9 月之前 |
|
ggml-impl.h
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
7 月之前 |
|
ggml-opt.cpp
|
6c35981a64
mnist: fix segmentation fault (ggml/1227)
|
8 月之前 |
|
ggml-quants.c
|
13b0a04597
whisper: remove MSVC warnings pragmas (whisper/3090)
|
8 月之前 |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 年之前 |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 年之前 |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 年之前 |
|
ggml.c
|
a7b8d35f78
sync : whisper.cpp (ggml/1250)
|
7 月之前 |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
7 月之前 |
|
gguf.cpp
|
7675c555a1
gguf: fix failure on version == 0 (#13956)
|
7 月之前 |
Masato Nakasaka
669c13e0f6
vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs (#14001)