Enable overlap scheduler by default for the triton attention backend (#2105)

This commit is contained in:
Lianmin Zheng
2024-11-20 02:58:35 -08:00
committed by GitHub
parent 56a347f7d3
commit 722530fa01
6 changed files with 21 additions and 24 deletions

View File

@@ -2,3 +2,4 @@
kill -9 $(ps aux | grep 'multiprocessing.spawn' | grep -v 'grep' | awk '{print $2}')
kill -9 $(ps aux | grep 'sglang.launch_server' | grep -v 'grep' | awk '{print $2}')
kill -9 $(ps aux | grep 'sglang.bench' | grep -v 'grep' | awk '{print $2}')