Skip to content
nv-accelerate-v100

Enabled configurable auto Tensor Parallelism (TP) for the inference of diverse models #12810

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 #12810

Re-run triggered January 21, 2025 19:57
@loadamsloadams
#6553
gyou2021:configurable_autoTP
Status Success
Total duration 7m 34s
Artifacts –

nv-accelerate-v100.yml

on: pull_request
unit-tests
7m 25s
unit-tests
Fit to window
Zoom out
Zoom in