mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-10-10 08:15:40 +02:00
* CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID * fix logic for RoPE support, CUDA graphs
* CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID * fix logic for RoPE support, CUDA graphs