A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 13, 08:15 UTC
[BugFix][ROCm] Fix `get_cu_count` missing variable error (#28608)
Signed-off-by: ganyi <ygan@amd.com>
Pleaplusone committed
Nov 13, 2025 at 13:18 UTC
7dca0c90cbd221bdc2650a46ba04a288fc95fd94
1 file changed
+1
-1
vllm/utils/platform_utils.py
+1
-1
@@ -24,7 +24,7 @@ def xpu_is_initialized() -> bool:
24
return torch.xpu.is_initialized()
25
26
27
-def get_cu_count(cls, device_id: int = 0) -> int:
27
+def get_cu_count(device_id: int = 0) -> int:
28
"""Returns the total number of compute units (CU) on single GPU."""
29
return torch.cuda.get_device_properties(device_id).multi_processor_count
30