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
[Testing] Add test_config.py to CI (#3437)
Cade Daniel committed
Mar 18, 2024 at 12:48 UTC
482b0adf1b689a3fb6cdd5374b57ac75f1591d6a
1 file changed
+1
-1
.buildkite/test-pipeline.yaml
+1
-1
@@ -28,7 +28,7 @@ steps:
28
num_gpus: 2 # only support 1 or 2 for now.
29
30
- label: Engine Test
31
- command: pytest -v -s engine tokenization test_sequence.py
31
+ command: pytest -v -s engine tokenization test_sequence.py test_config.py
32
33
- label: Entrypoints Test
34
command: pytest -v -s entrypoints