[Fix] DeepEP Compatibility with Low Latency (#5068)

Co-authored-by: ch-wan <cwan39@gatech.edu>
2025-04-09 11:31:31 +08:00
parent aac531c53b
commit bc3f6db2dd
4 changed files with 146 additions and 118 deletions
--- a/python/sglang/srt/model_executor/forward_batch_info.py
+++ b/python/sglang/srt/model_executor/forward_batch_info.py
@@ -72,7 +72,7 @@ class ForwardMode(IntEnum):
    DUMMY_FIRST = auto()

    def is_prefill(self):
-        return self == ForwardMode.PREFILL
+        return self.is_extend()

    def is_extend(self):
        return (