[Fix] Compatibility of window attention and cuda graph (#1090)

Browse Source

...

This commit is contained in:

Ying Sheng

2024-08-14 10:37:01 -07:00

committed by GitHub

parent a34dd86a7d

commit 96a2093ef0

7 changed files with 70 additions and 39 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1

python/sglang/test/long_prompt.txt Normal file

File diff suppressed because one or more lines are too long