chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

bugfix: prioritize init_npu_backend to fix various initialization bugs (#17652)

Browse Source
This commit is contained in:
jianzhao-xu
2026-02-24 12:25:20 +08:00
committed by GitHub
parent 59e7ea99c5
commit d8ef33a551
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
python/sglang/srt/model_executor/model_runner.py
View File

@@ -193,11 +193,6 @@ _is_npu = is_npu()
_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",

7
python/sglang/srt/server_args.py
View File

@@ -885,7 +885,12 @@ class ServerArgs:
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)