[1/2] Support deterministic inference with flashinfer attention backend (#10645)

Co-authored-by: hebiao064 <hebiaobuaa@gmail.com> Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
2025-09-19 23:34:29 -07:00
parent 1d1ce62495
commit 8ecef73f12
10 changed files with 427 additions and 6 deletions
--- a/python/sglang/srt/managers/schedule_batch.py
+++ b/python/sglang/srt/managers/schedule_batch.py
@@ -111,6 +111,7 @@ GLOBAL_SERVER_ARGS_KEYS = [
    "enable_symm_mem",
    "enable_custom_logit_processor",
    "disaggregation_mode",
+    "enable_deterministic_inference",
 ]

 # Put some global args for easy access