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
Jeff Bolz fadb3233b6 vulkan: optimize flash attention split_k_reduce (llama/14554) 
* vulkan: allow FA split_k with smaller KV values

* vulkan: spread split_k_reduce work across more threads

k_num can get rather large. Use the whole workgroup to reduce the M/L values.

Launch a thread for each element in the HSV dimension of the output. Helps a
lot for large HSV (like deepseek).
 		2025-07-12 19:23:56 +03:00
..
ggml-amx ggml : adapt AMX to tensor->grad removal (llama/0) 2024-11-20 21:00:08 +02:00
ggml-blas cmake : Fix broken CMake error messages (ggml/1252) 2025-06-01 15:14:44 +03:00
ggml-cann CANN: Replace aclrtMemsetSync with aclnnInplaceZero operator (llama/14002) 2025-07-12 19:23:56 +03:00
ggml-cpu ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) 2025-07-12 19:23:56 +03:00
ggml-cuda cuda : fix rope with partial rotation and non-cont src (llama/14580) 2025-07-12 19:23:56 +03:00
ggml-hip HIP: disable rocwmma on gfx12 by default until rocm 7.0 (llama/14202) 2025-06-18 12:40:34 +03:00
ggml-kompute llama : add Qwen2VL support + multimodal RoPE (llama/10361) 2024-12-18 12:52:16 +02:00
ggml-metal metal : disable fast math in all quantize kernels (llama/14528) 2025-07-12 19:23:56 +03:00
ggml-musa musa: enable fp16 mma (all) and cublas on qy2 (llama/13842) 2025-07-01 17:54:53 +03:00
ggml-opencl opencl: add GELU_ERF (llama/14476) 2025-07-12 19:23:56 +03:00
ggml-rpc rpc : nicer error messages for RPC server crash (llama/14076) 2025-06-18 12:40:34 +03:00
ggml-sycl cuda : fix rope with partial rotation and non-cont src (llama/14580) 2025-07-12 19:23:56 +03:00
ggml-vulkan vulkan: optimize flash attention split_k_reduce (llama/14554) 2025-07-12 19:23:56 +03:00
CMakeLists.txt Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286) 2025-06-21 07:34:17 +03:00
ggml-alloc.c ggml: Don't assert fail when tensor data changes (llama/13222) 2025-05-07 15:39:32 +03:00
ggml-backend-impl.h ggml : upgrade init_tensor API to return a ggml_status (llama/11854) 2025-03-08 15:13:01 +02:00
ggml-backend-reg.cpp build : suppress gcc15 compile warnings (llama/14261) 2025-06-21 07:34:17 +03:00
ggml-backend.cpp vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 2025-07-01 17:54:53 +03:00
ggml-common.h ggml-cpu : split arch-specific implementations (llama/13892) 2025-06-10 12:40:33 +03:00
ggml-impl.h vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 2025-07-01 17:54:53 +03:00
ggml-opt.cpp mnist: fix segmentation fault (ggml/1227) 2025-05-19 14:58:39 +03:00
ggml-quants.c ggml-quants : rename best_mad to best_error (ggml/1283) 2025-07-01 17:54:53 +03:00
ggml-quants.h ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
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 : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) 2025-07-12 19:23:56 +03:00
ggml.cpp ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 2025-05-29 09:56:26 +03:00
gguf.cpp ggml : do not output unprintable characters on GGUF load failure (llama/14381) 2025-07-01 17:54:53 +03:00