Files
whisper.cpp/ggml
Siavash Norouzi c6135ac226 ggml-cuda: fix divergent barrier in f16 flash attention (llama/27870)
* ggml-cuda: fix divergent barrier in f16 flash attention

* ggml-cuda: avoid duplicate metadata pointer setup
2026-09-14 20:45:06 +03:00
..