PR slow CI

Remove graph breaks for torch.compile() in flash_attention_forward when Lllama Model is padding free tuned #7878

Sign in to view logs

Re-run triggered October 18, 2024 11:54

#33932

Abhishek-TAMU:compile_llama

Status Skipped

Total duration 5s

Artifacts –

self-pr-slow-ci.yml

on: pull_request

Find models to run slow tests

Matrix: Run all tests for the model