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 16, 02:00 UTC
fix: update platform detection for M-series arm based MacBook processors (#12227)
Signed-off-by: isikhi <huseyin.isik000@gmail.com>
Işık committed
Jan 20, 2025 at 22:23 UTC
af69a6aded526343db8d4a199cdfd1bb84134201
1 file changed
+4
vllm/platforms/__init__.py
+4
@@ -101,6 +101,10 @@ def cpu_platform_plugin() -> Optional[str]:
101
try:
102
from importlib.metadata import version
103
is_cpu = "cpu" in version("vllm")
104
+ if is_cpu == False:
105
+ import platform
106
+ is_cpu = platform.machine().lower().startswith("arm")
107
+
108
except Exception:
109
pass
110