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 17, 04:15 UTC
Fix building from source on WSL (#3112)
Billy Cao committed
Mar 1, 2024 at 03:13 UTC
2c08ff23c07f2f8d51da8e1783c5346dccc1fd12
1 file changed
+1
-1
setup.py
+1
-1
@@ -36,7 +36,7 @@ def _is_neuron() -> bool:
36
torch_neuronx_installed = True
37
try:
38
subprocess.run(["neuron-ls"], capture_output=True, check=True)
39
- except FileNotFoundError:
39
+ except (FileNotFoundError, PermissionError):
40
torch_neuronx_installed = False
41
return torch_neuronx_installed
42