SIGN IN SIGN UP

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

[Bugfix][CI] Move resolving cudagraph_mode before initializing attn_metadata_builder (#27427)

Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
F
fhl2000 committed
85fee74b337522f7e0807fc100b9e00682ff45e1
Parent: 8dbe0c5
Committed by GitHub <noreply@github.com> on 10/24/2025, 3:31:14 AM