Skip to content
nv-torch-latest-v100

Extend DeepSpeed inference initialization API with a 'quantize_groups' argument #12999

Sign in to view logs

Extend DeepSpeed inference initialization API with a 'quantize_groups' argument

Extend DeepSpeed inference initialization API with a 'quantize_groups' argument #12999

Re-run triggered January 24, 2025 22:27
@loadamsloadams
#3519
sakogan:quant-params
Status Success
Total duration 1h 32m 22s
Artifacts –

nv-torch-latest-v100.yml

on: pull_request
unit-tests
1h 32m
unit-tests
Fit to window
Zoom out
Zoom in