[Scheduler] validate max_num_batched_tokens and max_model_len in AscendSchedulerConfig #9746
Triggered via pull request
August 20, 2025 18:06
Status
Success
Total duration
2h 22m 8s
Artifacts
–
vllm_ascend_test.yaml
on: pull_request
Matrix: singlecard e2e test
Matrix: unit test
Matrix: multicard e2e test