mirror of
https://github.com/wassname/vllm.git
synced 2026-09-28 14:45:02 +08:00
Fixes a typo about 'max_decode_seq_len' which causes crashes with cuda graph. (#9285)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
This commit is contained in: