Fix multi-image and 2x speed improvements (DS-VL2) #157
Conversation
This file contains 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
Blaizzy
changed the title
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Outdated suggestions cannot be applied.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.
Summary
This PR introduces critical improvements and optimizations for multi-image inference, resulting in significant performance gains.
Key Updates
Fixes Multi-Image Inference
Resolved issues to ensure correct and efficient handling of multi-image inputs.
Achieves ~2x Speedup
Improved processing efficiency for both prompt handling and token generation, nearly doubling performance.
Performance Metrics
Single-Image Inference
Performance remains consistent and stable, as shown below:
Multi-Image Inference
Significant improvements are evident in multi-image inference, as illustrated below:
