Skip to content

[Fix] Only add SM90 and SM100 to check for auto-enabling TRT Allreduce Fusion #16283

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

Open
b8zhong wants to merge 2 commits into
base: main
Choose a base branch
from
+2 −2
Open

[Fix] Only add SM90 and SM100 to check for auto-enabling TRT Allreduce Fusion #16283

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ccffa7
more
b8zhong Jan 2, 2026
436ce74
more
b8zhong Jan 2, 2026
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
4 changes: 2 additions & 2 deletions python/sglang/srt/server_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1501,7 +1501,7 @@ def _handle_model_specific_adjustments(self):
f"Overlap scheduler is disabled when using sparse head for embedding model."
)

# TRTLLM AllReduce Fusion supports SM90/100/120, enable it by default
# TRTLLM AllReduce Fusion supports SM90/100, enable it by default
# for models with explicit support (DeepseekV3, GptOss, Glm4Moe, Qwen3Moe)
# TODO: currently, it is only supported in the single node scenario. https://github.com/flashinfer-ai/flashinfer/issues/2006
# TODO: there is currently a bug on H20 device specifically, https://github.com/flashinfer-ai/flashinfer/issues/2204
Expand All @@ -1518,7 +1518,7 @@ def _handle_model_specific_adjustments(self):
"Glm4MoeForCausalLM",
"Qwen3MoeForCausalLM",
]
and (is_sm90_supported() or is_blackwell_supported())
and (is_sm90_supported() or is_sm100_supported())
and not self.enable_dp_attention
and self.nnodes == 1
and not is_h20_device
Expand Down
Loading