feat: implement inference server by using vllm #1269
Triggered via pull request
October 14, 2024 22:35
zhuangqh
Status
Cancelled
Total duration
10h 3m 6s
Artifacts
–
Annotations
1 error
|
run-e2e (gpuprovisioner) / e2e-tests-gpuprovisioner
Canceling since a higher priority waiting request for 'pr-e2e-test-zhuangqh/support-vllm' exists
|