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 15, 16:00 UTC
[misc] improve error message for "Failed to infer device type" (#15994)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Apr 3, 2025 at 14:45 UTC
5e125e74d1b9739025ccb81106e28ce9b0dd4ea5
1 file changed
+4
-1
vllm/config.py
+4
-1
@@ -1875,7 +1875,10 @@ class DeviceConfig:
1875
from vllm.platforms import current_platform
1876
self.device_type = current_platform.device_type
1877
if not self.device_type:
1878
- raise RuntimeError("Failed to infer device type")
1878
+ raise RuntimeError(
1879
+ "Failed to infer device type, please set "
1880
+ "the environment variable `VLLM_LOGGING_LEVEL=DEBUG` "
1881
+ "to turn on verbose logging to help debug the issue.")
1882
else:
1883
# Device type is assigned explicitly
1884
self.device_type = device