Skip to content

Add explicit disable flag for FlashInfer allreduce fusion #21446

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
Fridge003 merged 2 commits into from
Mar 31, 2026
Merged

Add explicit disable flag for FlashInfer allreduce fusion #21446

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
357b61b
upd
mmangkad Mar 26, 2026
d1ab475
upd
mmangkad Mar 29, 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
14 changes: 14 additions & 0 deletions python/sglang/srt/server_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -518,6 +518,7 @@ class ServerArgs:
moe_runner_backend: str = "auto"
flashinfer_mxfp4_moe_precision: Literal["default", "bf16"] = "default"
enable_flashinfer_allreduce_fusion: bool = False
enforce_disable_flashinfer_allreduce_fusion: bool = False
enable_aiter_allreduce_fusion: bool = False
deepep_mode: Literal["auto", "normal", "low_latency"] = "auto"
ep_num_redundant_experts: int = 0
Expand Down Expand Up @@ -2080,6 +2081,14 @@ def _handle_model_specific_adjustments(self):
):
self.enable_flashinfer_allreduce_fusion = True

# Apply enforce_disable_flashinfer_allreduce_fusion after all model-specific adjustments
if self.enforce_disable_flashinfer_allreduce_fusion:
self.enable_flashinfer_allreduce_fusion = False
logger.info(
"FlashInfer allreduce fusion is forcibly disabled "
"via --enforce-disable-flashinfer-allreduce-fusion."
)

def _handle_mamba_radix_cache(
self,
model_arch: str,
Expand Down Expand Up @@ -4841,6 +4850,11 @@ def add_cli_args(parser: argparse.ArgumentParser):
action="store_true",
help="Enable FlashInfer allreduce fusion with Residual RMSNorm.",
)
parser.add_argument(
"--enforce-disable-flashinfer-allreduce-fusion",
action="store_true",
help="Enforce disable FlashInfer allreduce fusion.",
)
parser.add_argument(
"--enable-aiter-allreduce-fusion",
action="store_true",
Expand Down
Loading