Skip to content

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #11491

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #11491

Re-run triggered February 5, 2025 01:47
Status Success
Total duration 2m 5s
Artifacts

python.yml

on: pull_request
Matrix: unit-tests
Fit to window
Zoom out
Zoom in