public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src
History
Ruben Ortlam 76d0934287
vulkan: use vec dot for matrix matrix multiplications (llama/16056) 
* vulkan: Change the mul_mm shared memory and register caching system to use vec2 instead of scalars, to enable using dot2 instructions

* use fma instead of dot to fix Nvidia and Apple performance issues
 		2025-09-20 13:46:39 +03:00
..
ggml-amx ggml : adapt AMX to tensor->grad removal (llama/0) 2024-11-20 21:00:08 +02:00
ggml-blas rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-cann rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-cpu ggml : refactor forward_dup for cpu backend (llama/16062) 2025-09-20 13:46:39 +03:00
ggml-cuda rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-hip HIP: bump requirement to rocm 6.1 (llama/15296) 2025-08-18 20:30:45 +03:00
ggml-metal rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-musa CUDA: replace GGML_CUDA_F16 with CUDA arch checks (llama/15433) 2025-09-20 13:42:38 +03:00
ggml-opencl opencl: optimize mxfp4 kernels (llama/16037) 2025-09-20 13:46:39 +03:00
ggml-rpc rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-sycl rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-vulkan vulkan: use vec dot for matrix matrix multiplications (llama/16056) 2025-09-20 13:46:39 +03:00
ggml-webgpu rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-zdnn rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
CMakeLists.txt cmake : fix static linking for OpenMP on Unix-like systems (llama/16031) 2025-09-20 13:46:39 +03:00
ggml-alloc.c llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-backend-impl.h rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-backend-reg.cpp ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (llama/15797) 2025-09-20 13:45:28 +03:00
ggml-backend.cpp rename optimize_graph to graph_optimize (llama/16082) 2025-09-20 13:46:39 +03:00
ggml-common.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-impl.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-opt.cpp finetune: SGD optimizer, more CLI args (llama/13873) 2025-08-18 20:30:45 +03:00
ggml-quants.c ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (llama/15379) 2025-08-18 20:30:45 +03:00
ggml-quants.h llama : add gpt-oss (llama/15091) 2025-08-18 20:30:45 +03:00
ggml-threading.cpp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
ggml-threading.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797) 2024-12-18 12:52:16 +02:00
ggml.c ggml : fix padding in timestep embedding kernels (llama/15932) 2025-09-20 13:45:30 +03:00
ggml.cpp ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 2025-05-29 09:56:26 +03:00
gguf.cpp ggml : prevent integer overflow in gguf tensor size calculation (llama/14595) 2025-07-12 19:23:56 +03:00