Skip to content

fuse fp8 quant in kv copying and add flashinfer decode mla operator in the attention module #641

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 #641

Triggered via pull request February 25, 2025 07:58
Status Success
Total duration 31s
Artifacts

pre-commit.yml

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