Skip to content
Back to pull request #31771

Speedup model init on CPU (by 10x+ for llama-3-8B as one example) #2803

Sign in to view logs

Speedup model init on CPU (by 10x+ for llama-3-8B as one example)

Speedup model init on CPU (by 10x+ for llama-3-8B as one example) #2803

Triggered via pull request July 16, 2024 12:56
@muellerzrmuellerzr
synchronize #31771
muellerzr-speedup-inference
Status Success
Total duration 29s
Artifacts –

self-pr-slow-ci.yml

on: pull_request
Find models to run slow tests
18s
Find models to run slow tests
Matrix: Run all tests for the model
Fit to window
Zoom out
Zoom in