Qwen3 model

[lastshogun13]

Description of Changes

This PR adds support for Qwen3 model (qwen.qwen3-235b-a22b-2507-v1:0, qwen.qwen3-32b-v1:0, qwen.qwen3-coder-480b-a35b-v1:0, qwen.qwen3-coder-30b-a3b-v1:0, ) to the Generative AI Use Cases application.

Changes include:

• Added Qwen3 model configuration to the backend model registry (packages/cdk/lambda/utils/models.ts)
• Added model metadata for Qwen3 in the common package (packages/common/src/application/model.ts)
  • Model supports text and document features (MODEL_FEATURE.TEXT_DOC)
  • Display name: "Qwen3"
• Updated deployment option documentation in English, Japanese, and Korean (docs/*/DEPLOY_OPTION.md)
  • Added Qwen3 to the list of supported text generation models
  • Added configuration examples with us-west-2 region specification
  • Added to cross-region inference examples and config preset examples

Impact on existing users:

• N/A

Checklist

• Modified relevant documentation
• Verified operation in local environment
• Executed npm run cdk:test and if there are snapshot differences, execute npm run cdk:test:update-snapshot to update snapshots

Related Issues

N/A

[kazuhitogo]

There is a problem with the operation check

[kazuhitogo]

Only Qwen3 32B returns an error (the other three worked fine), but did it work in your environment?

There is a problem with the operation check

[lastshogun13]

Adjusted their maxTokens parameters based on actual testing to ensure they all work correctly.

The token limits were verified through systematic testing with AWS Bedrock:

• qwen3-235b-a22b-2507: 196,608 tokens
• qwen3-32b: 16,384 tokens
• qwen3-coder-480b-a35b: 65,536 tokens
• qwen3-coder-30b-a3b: 196,608 tokens

All models have been tested and confirmed working with these configurations.

Note: The lower token limit for qwen3-coder-480b-a35b was determined through direct Bedrock API testing. The reason for this limitation is currently unknown.

[kazuhitogo]

LGTM, Thank you.