Decouple vLLM engine and GRPOTrainer. #3911
Merged
Conversation
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
hjh0119
commented
Apr 22, 2025
Comment on lines
+1208
to
+1218
| def _process_infer_requests_images(self, infer_requests: List[InferRequest]): | ||
| import base64 | ||
| if not any('images' in request for request in infer_requests): | ||
| return | ||
| for request in infer_requests: | ||
| if 'images' not in request: | ||
| continue | ||
| for i, img in enumerate(request['images']): | ||
| if 'bytes' in img and img['bytes']: | ||
| request['images'][i] = base64.b64encode(img['bytes']).decode('utf-8') | ||
| return |
There was a problem hiding this comment.
Are there any other cases where images is not a string?
hjh0119
commented
Apr 22, 2025
tastelikefeet
approved these changes
Apr 22, 2025
Jintao-Huang
approved these changes
Apr 22, 2025
|
32B Full training curve
|
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Outdated suggestions cannot be applied.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.
PR type
PR information
Decouple vLLM engine and GRPOTrainer to support external vLLM server.
related issue/pr:
huggingface/trl#3094
#3817
#3712
32B Full GRPO training script
related issue/pr:
#3871
#3887
Experiment results
Paste your experiment result here(if needed).