Skip to content

feat(rocm): f32-query decode GQA kernel with bf16 and fp8 KV cache support - #8

Closed
ghazni101 wants to merge 13 commits into
mainfrom
row/fp8-kv-decode-attn
Closed

feat(rocm): f32-query decode GQA kernel with bf16 and fp8 KV cache support#8
ghazni101 wants to merge 13 commits into
mainfrom
row/fp8-kv-decode-attn

docs(ENVIRONMENT): document VT_ATTN_DECODE_GQA4, the f32-query GQA4 gate

a05d760
Select commit
Loading
Failed to load commit list.

There are no checks for this commit