Skip to content

support qwen35 moe gdn sp#222

Merged
tpx818 merged 1 commit into
modelscope:mainfrom
meichangsu1:qwe35_moe
Jun 10, 2026
Merged

support qwen35 moe gdn sp#222
tpx818 merged 1 commit into
modelscope:mainfrom
meichangsu1:qwe35_moe

Conversation

@meichangsu1

Copy link
Copy Markdown
Collaborator

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

支持qwen3.5 moe gdn sp

Experiment results

5dafa6de8efe0d4b3ed28e1ea71a3b54

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request extends the sequence parallel strategy to support the Qwen 3.5 MoE model type by dynamically importing and patching both Qwen3_5GatedDeltaNet and Qwen3_5MoeGatedDeltaNet classes. The review feedback recommends reusing the newly introduced _iter_qwen35_gated_delta_net_classes helper function in __init__.py to avoid duplicating the try-except import logic, keeping the codebase DRY.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

Comment thread src/twinkle/model/transformers/strategy/sequence_parallel/__init__.py Outdated
@tpx818 tpx818 merged commit de231c8 into modelscope:main Jun 10, 2026
1 of 3 checks 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.

2 participants