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, 19:30 UTC
[misc] add commit id in collect env (#7405)
youkaichao committed
Aug 11, 2024 at 15:40 UTC
6c8e595710fb3fdcf868bf8bfa5863399b287b43
1 file changed
+3
-2
collect_env.py
+3
-2
@@ -265,8 +265,9 @@ def get_neuron_sdk_version(run_lambda):
265
def get_vllm_version():
266
try:
267
import vllm
268
- return vllm.__version__
269
- except ImportError:
268
+ return vllm.__version__ + "@" + vllm.__commit__
269
+ except Exception:
270
+ # old version of vllm does not have __commit__
271
return 'N/A'
272
273