Skip to content

feat: add Qwen3-ASR-1.7B smoke test and benchmark#5995

Open
Jyothirmaikottu wants to merge 5 commits intomainfrom
add-qwen3-asr-benchmark
Open

feat: add Qwen3-ASR-1.7B smoke test and benchmark#5995
Jyothirmaikottu wants to merge 5 commits intomainfrom
add-qwen3-asr-benchmark

Conversation

@Jyothirmaikottu
Copy link
Copy Markdown
Contributor

Add ASR-specific test scripts for Qwen3-ASR-1.7B model:

  • Smoke test validates chat completions with audio_url and OpenAI transcription API endpoints
  • Benchmark measures throughput (tokens/s) and latency (p50/p95/p99) with configurable pass/fail thresholds
  • Support custom test_script in model-tests config and workflows
  • Model weights uploaded to s3://dlc-cicd-models/llm-models/

Purpose

Test Plan

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 ASR-specific test scripts for Qwen3-ASR-1.7B model:
- Smoke test validates chat completions with audio_url and
  OpenAI transcription API endpoints
- Benchmark measures throughput (tokens/s) and latency (p50/p95/p99)
  with configurable pass/fail thresholds
- Support custom test_script in model-tests config and workflows
- Model weights uploaded to s3://dlc-cicd-models/llm-models/
@Jyothirmaikottu Jyothirmaikottu force-pushed the add-qwen3-asr-benchmark branch from f2d83b8 to 38314cb Compare April 24, 2026 18:30
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