Skip to content

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #13173

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

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #13173

Re-run triggered February 20, 2025 13:18
Status Success
Total duration 8m 18s
Artifacts

nv-accelerate-v100.yml

on: pull_request
Fit to window
Zoom out
Zoom in