Skip to content

[fix] put cpu in the first priority in get_device() #7752

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 1 commit into from
Jul 3, 2025
Merged

[fix] put cpu in the first priority in get_device() #7752

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
18 changes: 9 additions & 9 deletions python/sglang/srt/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1443,6 +1443,15 @@ def is_habana_available() -> bool:

@lru_cache(maxsize=8)
def get_device(device_id: Optional[int] = None) -> str:
if is_cpu():
if cpu_has_amx_support():
logger.info("Intel AMX is detected, using CPU with Intel AMX support.")
else:
logger.warning(
"CPU device enabled, using torch native backend, low performance expected."
)
return "cpu"

if hasattr(torch, "cuda") and torch.cuda.is_available():
if device_id is None:
return "cuda"
Expand Down Expand Up @@ -1471,15 +1480,6 @@ def get_device(device_id: Optional[int] = None) -> str:
"Habana frameworks detected, but failed to import 'habana_frameworks.torch.hpu'."
)

if is_cpu():
if cpu_has_amx_support():
logger.info("Intel AMX is detected, using CPU with Intel AMX support.")
else:
logger.warning(
"CPU device enabled, using torch native backend, low performance expected."
)
return "cpu"

raise RuntimeError("No accelerator (CUDA, XPU, HPU) is available.")


Expand Down
Loading