setup vllm test logics.
1. install wheels generated from previous build stage
2. generate and install vllm test pkg list on run time based on the torch wheels in the instance
3. run test based on the pre-defined test plan
notice the test-plan format is temporary for some basic vllm testing
Pull Request resolved: https://github.com/pytorch/pytorch/pull/160361
Approved by: https://github.com/atalman, https://github.com/huydhn
# set up vllm build logic
- dockerfile: please notice the dockfile introduced here is only temporary, once we migrate this file to vllm, we will fetch it directly from there
- VllmBuildRunner:
- implement logic to prepare and run vllm build with dockerfile
-
Pull Request resolved: https://github.com/pytorch/pytorch/pull/160089
Approved by: https://github.com/huydhn
ghstack dependencies: #160043