Skip to content

bugfix: prioritize init_npu_backend to fix various initialization bugs #17652

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
Hide-on-bushsh wants to merge 3 commits into
base: main
Choose a base branch
from
+6 −6
Open

bugfix: prioritize init_npu_backend to fix various initialization bugs #17652

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e79178e
bugfix: nccl adapt --encoder-only on the npu
Hide-on-bushsh Feb 2, 2026
9df128c
Merge branch 'main' into bug
iforgetmyname Feb 3, 2026
cd11b27
Merge branch 'main' into bug
iforgetmyname Feb 4, 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
5 changes: 0 additions & 5 deletions python/sglang/srt/model_executor/model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,11 +186,6 @@
_is_cpu_amx_available = cpu_has_amx_support()
_is_cpu_arm64 = is_host_cpu_arm64()

if _is_npu:
from sglang.srt.hardware_backend.npu.utils import init_npu_backend

init_npu_backend()

MLA_ATTENTION_BACKENDS = [
"aiter",
"flashinfer",
Expand Down
7 changes: 6 additions & 1 deletion python/sglang/srt/server_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -889,7 +889,12 @@ def _handle_cpu_backends(self):

def _handle_npu_backends(self):
if self.device == "npu":
from sglang.srt.hardware_backend.npu.utils import set_default_server_args
from sglang.srt.hardware_backend.npu.utils import (
init_npu_backend,
set_default_server_args,
)

init_npu_backend()

set_default_server_args(self)

Expand Down
Loading