Roadmap for adding vision language model support#1560
Draft
Jackmin801 wants to merge 1 commit intomainfrom
Draft
Roadmap for adding vision language model support#1560Jackmin801 wants to merge 1 commit intomainfrom
Jackmin801 wants to merge 1 commit intomainfrom
Conversation
Add comprehensive analysis document outlining the changes required to support vision language models like Qwen3-VL-8B-Instruct in Prime-RL's SFT and RL training pipelines. Key areas covered: - Current architecture overview and component interactions - Qwen3-VL model architecture requirements - Core changes needed for model loading, forward pass, and data structures - SFT and RL pipeline modifications - Inference server integration with vLLM - FSDP sharding for vision encoders - Implementation roadmap with phased approach - Technical considerations for memory, batching, and serialization
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add comprehensive analysis document outlining the changes required to support vision language models like Qwen3-VL-8B-Instruct in Prime-RL's SFT and RL training pipelines.
Key areas covered: