Skip to content

fuse fp8 quant in kv copying and add flashinfer decode mla operator in the attention module #637

fuse fp8 quant in kv copying and add flashinfer decode mla operator in the attention module

fuse fp8 quant in kv copying and add flashinfer decode mla operator in the attention module #637

Triggered via pull request February 24, 2025 09:26
Status Success
Total duration 30s
Artifacts

pre-commit.yml

on: pull_request
pre-commit
20s
pre-commit
Fit to window
Zoom out
Zoom in