mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-10-09 15:55:37 +02:00
Jeff Bolz
85d4d2c875
The scalar FA shader already handled multiples of 8. The coopmat1 FA shader assumed 16x16x16 and the shared memory allocations need the HSK dimensions padded to a multiple of 16. NVIDIA's coopmat2 implementation requires multiples of 16 for N and K, and needs the matrix dimensions padded and loads clamped. Store the FA pipelines in a map, indexed by the pipeline state.