Skip to content

Fix dpsk-r1-fp4 launching crash #12063

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
hnyls2002 merged 1 commit into from
Oct 24, 2025
Merged

Fix dpsk-r1-fp4 launching crash #12063

Show file tree
Hide file tree
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
12 changes: 5 additions & 7 deletions python/sglang/srt/layers/quantization/mxfp4.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -587,13 +587,11 @@ def create_moe_runner(
self, layer: torch.nn.Module, moe_runner_config: MoeRunnerConfig
):
self.moe_runner_config = moe_runner_config
backend = get_moe_runner_backend()
if backend.is_auto():
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
Comment on lines +590 to +594
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This hardcodes the backend selection to avoid a crash with unsupported backends. As noted in the PR description, this is a temporary fix. It would be beneficial to add a comment here to inform future developers about this, and that it should be refactored for more flexible backend selection.

Suggested change
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
# TODO(https://github.com/sgl-project/sglang/issues/12059): This is a temporary fix to avoid a crash with unsupported backends.
# This should be refactored for more flexible backend selection in the future.
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)

self.runner = MoeRunner(backend, moe_runner_config)

def apply(
Expand Down
19 changes: 6 additions & 13 deletions python/sglang/srt/layers/quantization/unquant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,7 @@

from sglang.srt.custom_op import CustomOp
from sglang.srt.layers.amx_utils import _amx_process_weight_after_loading
from sglang.srt.layers.moe import (
MoeRunner,
MoeRunnerBackend,
MoeRunnerConfig,
get_moe_runner_backend,
)
from sglang.srt.layers.moe import MoeRunner, MoeRunnerBackend, MoeRunnerConfig
from sglang.srt.layers.moe.moe_runner.triton import TritonMoeQuantInfo
from sglang.srt.layers.quantization.base_config import (
FusedMoEMethodBase,
Expand Down Expand Up @@ -225,13 +220,11 @@ def create_moe_runner(
self, layer: torch.nn.Module, moe_runner_config: MoeRunnerConfig
):
self.moe_runner_config = moe_runner_config
backend = get_moe_runner_backend()
if backend.is_auto():
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
Comment on lines +223 to +227
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This hardcodes the backend selection to avoid a crash with unsupported backends. As noted in the PR description, this is a temporary fix. It would be beneficial to add a comment here to inform future developers about this, and that it should be refactored for more flexible backend selection.

Suggested change
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)
# TODO(https://github.com/sgl-project/sglang/issues/12059): This is a temporary fix to avoid a crash with unsupported backends.
# This should be refactored for more flexible backend selection in the future.
backend = (
MoeRunnerBackend.TRITON_KERNELS
if self.use_triton_kernels
else MoeRunnerBackend.TRITON
)

self.runner = MoeRunner(backend, moe_runner_config)

def apply(
Expand Down
Loading