Skip to content

feat: update models to qwen3-coder series and optimize routing#5

Merged
wenmengzhou merged 1 commit intomainfrom
feat/update-qwen-coder-models
Jul 22, 2025
Merged

feat: update models to qwen3-coder series and optimize routing#5
wenmengzhou merged 1 commit intomainfrom
feat/update-qwen-coder-models

Conversation

@wenmengzhou
Copy link
Collaborator

  • Replace qwen3-235b-a22b with qwen3-coder-plus and qwen3-coder-flash
  • Optimize router configuration for different scenarios:
    • default/think/longContext: use qwen3-coder-plus (stronger model)
    • background: use qwen3-coder-flash (faster model)
  • Update test cases to validate new model configurations
  • Ensure all routing configurations work correctly

- Replace qwen3-235b-a22b with qwen3-coder-plus and qwen3-coder-flash
- Optimize router configuration for different scenarios:
  - default/think/longContext: use qwen3-coder-plus (stronger model)
  - background: use qwen3-coder-flash (faster model)
- Update test cases to validate new model configurations
- Ensure all routing configurations work correctly
@wenmengzhou wenmengzhou merged commit 34b2839 into main Jul 22, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant