Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #11441
This workflow is awaiting approval from a maintainer in #6553
Triggered via pull request
January 17, 2025 10:26
gyou2021
Status
Action required
Total duration
–
Artifacts
–
This workflow is awaiting approval from a maintainer in #6553
python.yml
on: pull_request
Matrix: unit-tests
Waiting for pending jobs