Skip to content

test(vllm): add MiniCPM5-1B model tests (smoke-test + sagemaker)#6321

Open
ytp327 wants to merge 2 commits into
aws:mainfrom
ytp327:validate-minicpm5-model-test
Open

test(vllm): add MiniCPM5-1B model tests (smoke-test + sagemaker)#6321
ytp327 wants to merge 2 commits into
aws:mainfrom
ytp327:validate-minicpm5-model-test

Conversation

@ytp327

@ytp327 ytp327 commented Jun 30, 2026

Copy link
Copy Markdown

Add MiniCPM5-1B (dense 1B LlamaForCausalLM, bf16) to the vLLM model-test config in both suites:

  • smoke-test: EC2 serving on x86-g6xl-runner, --max-model-len 8192
  • sagemaker: ml.g6.xlarge endpoint, /v1/chat/completions test case

Standard architecture, loads with plain vllm serve (no trust-remote-code). Validated offline on server-cuda-v2 / server-sagemaker-cuda-v2 at --max-model-len 8192. Model artifact uploaded to
s3://dlc-cicd-models/llm-models/minicpm5-1b.tar.gz.

Purpose

Test Plan

  1. Manually validate MiniCPM5-1B model works on EC2 and SageMaker DLC
  2. CI test

Test Result


Toggle if you are merging into master Branch

By default, docker image builds and tests are disabled. Two ways to run builds and tests:

  1. Using dlc_developer_config.toml
  2. Using this PR description (currently only supported for PyTorch, TensorFlow, vllm, and base images)
How to use the helper utility for updating dlc_developer_config.toml

Assuming your remote is called origin (you can find out more with git remote -v)...

  • Run default builds and tests for a particular buildspec - also commits and pushes changes to remote; Example:

python src/prepare_dlc_dev_environment.py -b </path/to/buildspec.yml> -cp origin

  • Enable specific tests for a buildspec or set of buildspecs - also commits and pushes changes to remote; Example:

python src/prepare_dlc_dev_environment.py -b </path/to/buildspec.yml> -t sanity_tests -cp origin

  • Restore TOML file when ready to merge

python src/prepare_dlc_dev_environment.py -rcp origin

NOTE: If you are creating a PR for a new framework version, please ensure success of the local, standard, rc, and efa sagemaker tests by updating the dlc_developer_config.toml file:

  • sagemaker_remote_tests = true
  • sagemaker_efa_tests = true
  • sagemaker_rc_tests = true
  • sagemaker_local_tests = true
How to use PR description Use the code block below to uncomment commands and run the PR CodeBuild jobs. There are two commands available:
  • # /buildspec <buildspec_path>
    • e.g.: # /buildspec pytorch/training/buildspec.yml
    • If this line is commented out, dlc_developer_config.toml will be used.
  • # /tests <test_list>
    • e.g.: # /tests sanity security ec2
    • If this line is commented out, it will run the default set of tests (same as the defaults in dlc_developer_config.toml): sanity, security, ec2, ecs, eks, sagemaker, sagemaker-local.
# /buildspec <buildspec_path>
# /tests <test_list>
Toggle if you are merging into main Branch

PR Checklist

  • [] I ran pre-commit run --all-files locally before creating this PR. (Read DEVELOPMENT.md for details).

Add MiniCPM5-1B (dense 1B LlamaForCausalLM, bf16) to the vLLM model-test
config in both suites:

- smoke-test: EC2 serving on x86-g6xl-runner, --max-model-len 8192
- sagemaker: ml.g6.xlarge endpoint, /v1/chat/completions test case

Standard architecture, loads with plain `vllm serve` (no trust-remote-code).
Validated offline on server-cuda-v2 / server-sagemaker-cuda-v2 at
--max-model-len 8192. Model artifact uploaded to
s3://dlc-cicd-models/llm-models/minicpm5-1b.tar.gz.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant