Skip to content

Fix reduce_scatterv producer contract for SUM_LEN #24785

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ch-wan merged 1 commit into from
May 10, 2026
+4 −2
Merged

Fix reduce_scatterv producer contract for SUM_LEN #24785

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions python/sglang/srt/layers/communicator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -700,9 +700,11 @@ def should_use_reduce_scatter(self, forward_batch: ForwardBatch):
if (
self._communicate_summable_tensor_pair_fn
is CommunicateSummableTensorPairFn._scatter_hidden_states
and forward_batch.dp_padding_mode.is_max_len()
):
return True
if should_use_dp_reduce_scatterv():
return True
if forward_batch.dp_padding_mode.is_max_len():
return True
if nsa_use_prefill_cp(forward_batch):
return True
if get_attn_tp_context().input_scattered and not self.is_last_layer:
Expand Down
Loading