inference: improve partitioned blending by introducing chunk index#712
Open
inference: improve partitioned blending by introducing chunk index#712
Conversation
This avoids the existing O(n^2) problem when the coordinates array was scanned linearly again and again for each chunk. This led to excessive S3 retrievals for the small coordinate arrays and subpar performance. Now S3 is also scanned for missing (empty) patches files beforehand and those are immediately skipped. The runtime is now dominated by accessing and decompressing the logit array.
To avoid large intermediate zarr arrays on s3
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment
|
…ses=1 and threshold modes
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Corresponding to version v30 as used in the latest workflow.
Doesn't merge cleanly with the latest changes for 3d ink detection, so will need some work.