GPU tests

llama 3.1 has correct `max_seq_len` for all versions #3098

Sign in to view logs

Re-run triggered December 24, 2024 18:51

#2203

akashc1:llama3_1-max_seq_len

Status Success

Total duration 48m 26s

Artifacts –

gpu_test.yaml

on: pull_request

Matrix: gpu_test