Skip to content
cpu-torch-latest

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #4396

Sign in to view logs

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

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #4396

Re-run triggered February 20, 2025 13:18
@delockdelock
#6553
gyou2021:configurable_autoTP
Status Success
Total duration 15m 44s
Artifacts –

cpu-torch-latest.yml

on: pull_request
unit-tests
15m 30s
unit-tests
Fit to window
Zoom out
Zoom in