whisper.cpp/ggml at f0768eb575f16d7eaa66c1fc507241f40d5081d2 - whisper.cpp - Gitea: Git with a cup of tea

public_git/whisper.cpp

mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-04 13:31:18 +02:00

Files

T

History

Johannes Gäßler f0768eb575 CUDA: larger SRAM reads for tile FA, AMD FP16 dot (llama/15927)

* CUDA: larger SRAM reads for tile FA, AMD FP16 dot

* fix logic for availability of v_dot2_f32_f16

2025-09-20 13:45:28 +03:00

..

ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094)

2025-08-18 20:30:45 +03:00

metal : make the backend async (llama/15906)

2025-09-20 13:44:27 +03:00

CUDA: larger SRAM reads for tile FA, AMD FP16 dot (llama/15927)

2025-09-20 13:45:28 +03:00

.gitignore

whisper : reorganize source code + improve CMake (#2256 )

2024-06-26 19:34:09 +03:00

CMakeLists.txt

ggml-cpu: drop support for nnpa intrinsics (llama/15821)

2025-09-20 13:42:50 +03:00