diff --git a/python/sglang/srt/models/deepseek_v4_replay_tail.py b/python/sglang/srt/models/deepseek_v4_replay_tail.py index 6b79e3efce..b5e5529298 100644 --- a/python/sglang/srt/models/deepseek_v4_replay_tail.py +++ b/python/sglang/srt/models/deepseek_v4_replay_tail.py @@ -4,8 +4,9 @@ Eager prefill steps replay them directly. A prefill-graph shape of at least ``SGLANG_DSV4_DECODER_TAIL_GRAPH_MIN_PREFILL_TOKENS`` tokens replays them from one eager break, through bridge buffers; smaller shapes keep the tail captured. -Under DP attention every rank replays the largest rank's bucket. MegaMoE agrees -on it through a host gather, so it needs the prefill graph off. +Under DP attention every rank replays the largest rank's bucket. In an eager step +MegaMoE agrees on it through a host gather; the prefill-graph break reads every +rank's rows from the pre-forward exchange. """ from __future__ import annotations @@ -282,7 +283,6 @@ class DecoderReplayTail: return ( num_tokens >= envs.SGLANG_DSV4_DECODER_TAIL_GRAPH_MIN_PREFILL_TOKENS.get() - and (get_parallel().attn_dp_size == 1 or get_moe_a2a_backend().is_none()) and tail.cp_metadata is None and not is_unified_kv_triton() # Encoder replay's folded rows are not checked against the exact tail.