New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixed sagemaker_llm_benchmark workflow configuration #2611

Merged

lxning merged 2 commits into master from test_wf_sm_llm_benchmark

Nov 25, 2024

Contributor

lxning commented Nov 25, 2024 •

edited

Loading

Description

Brief description of what this PR is about

If this change is a backward incompatible change, why must this change be made?
Interesting edge cases to note here

This PR includes:

extend workflow and aws client session timeout
add one runner to parallel lmi-dist and trtllm benchmark
fix typos

Test:

https://github.com/deepjavalibrary/djl-serving/actions/runs/12001588530
Cloudwatch dashboards

SM_LLM_benchmark_LMI_Llama-405b-fp8-series
SM_LLM_benchmark_LMI_Llama-70b-series
SM_LLM_benchmark_LMI_Llama-8b-series
SM_LLM_benchmark_TRTLLM_Llama-405b-fp8-series
SM_LLM_benchmark_TRTLLM_Llama-70b-series
SM_LLM_benchmark_TRTLLM_Llama-8b-series

lxning added 2 commits

November 24, 2024 10:39


          adjust workflow and aws timeout and region

747a68e


          fix typo

4360aa1

lxning requested review from zachgk and a team as code owners

November 25, 2024 18:03

siddvenk approved these changes

View reviewed changes

lxning merged commit 5129d14 into master

14 of 16 checks passed

lxning deleted the test_wf_sm_llm_benchmark branch

November 25, 2024 18:43

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet