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

[BugFix] Fix CPU inference failure (#15231)

Browse Source
This commit is contained in:
Yibo Cai
2025-12-15 21:32:41 -08:00
committed by GitHub
parent 02d24244e4
commit 22587bc0b4
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/server_args.py
+3 -1
View File
@@ -1443,7 +1443,9 @@ class ServerArgs:
# TODO: currently, it is only supported in the single node scenario. https://github.com/flashinfer-ai/flashinfer/issues/2006 # TODO: currently, it is only supported in the single node scenario. https://github.com/flashinfer-ai/flashinfer/issues/2006
# TODO: there is currently a bug on H20 device specifically, https://github.com/flashinfer-ai/flashinfer/issues/2204 # TODO: there is currently a bug on H20 device specifically, https://github.com/flashinfer-ai/flashinfer/issues/2204
device_name = get_device_name() device_name = get_device_name()
is_h20_device = "H20" in device_name and "H200" not in device_name is_h20_device = (
device_name and "H20" in device_name and "H200" not in device_name
)
if ( if (
not self.enable_flashinfer_allreduce_fusion not self.enable_flashinfer_allreduce_fusion
and model_arch and model_arch