nullname
8af1f5f430
ggml-hexagon: flash-attn opt (#19025)
* optimize flash attention kernel by improving score computation and online softmax update
* wip
* Refactor online softmax update in flash attention kernel for improved performance
* Optimize flash attention kernel by replacing float array with HVX_Vector for score computation
* wip
2026-01-23 22:02:07 -08:00
..
2025-08-07 13:45:41 +02:00
2026-01-19 20:03:19 +02:00
2026-01-23 22:02:07 -08:00
2024-07-13 18:12:39 +02:00
2025-12-31 18:54:43 +02:00