Commit Graph
2 Commits
Author SHA1 Message Date
Jeff Bolz dd9280a664 vulkan: Support asymmetric FA in scalar/mmq/coopmat1 paths (#22589) 2026-05-11 12:49:03 +02:00
Ruben Ortlam 75f3bc94e6 vulkan: Flash Attention DP4A shader for quantized KV cache (#20797)
* use integer dot product for quantized KV flash attention

* small improvements

* fix SHMEM_STAGING indexing

* add missing KV type quants

* fixes

* add supported quants to FA tests

* readd fast paths for <8bit quants

* fix mmq gate and shmem checks
2026-04-13 14:21:31 +02:00