Skip to content

Fix triton_kernels import error on some hardwares #11831

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
merged 3 commits into from
Oct 20, 2025
+1 −4
Merged

Fix triton_kernels import error on some hardwares #11831

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c06f033
Update unquant.py
fzyzcjy Oct 19, 2025
66f60df
Update unquant.py
fzyzcjy Oct 19, 2025
cf7fc02
Update unquant.py
fzyzcjy Oct 19, 2025
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
5 changes: 1 addition & 4 deletions python/sglang/srt/layers/quantization/unquant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
from __future__ import annotations

import importlib.util
from typing import TYPE_CHECKING, List, Optional

import torch
Expand Down Expand Up @@ -31,8 +30,6 @@
StandardDispatchOutput,
)

has_triton_kernels = importlib.util.find_spec("triton_kernels") is not None


_is_cpu_amx_available = cpu_has_amx_support()
_is_hip = is_hip()
Expand Down Expand Up @@ -143,7 +140,7 @@ def __init__(self, use_triton_kernels: bool = False):

self.triton_kernel_moe_forward = None
self.triton_kernel_moe_with_bias_forward = None
if torch.cuda.is_available() and has_triton_kernels:
if torch.cuda.is_available() and use_triton_kernels:
from sglang.srt.layers.moe.fused_moe_triton.triton_kernels_moe import (
triton_kernel_moe_forward as _tk_forward,
)
Expand Down
Loading