Repository navigation
Conversation
github-actions
Bot
added
testing
Contributor
|
This one is worth taking out of draft. I used it to test #31009 on the real GLM-5.3-Flash with CUDA: without it, two runs of the same master build don't give the same numbers, so you can't tell whether a change matches master. With it, the runs became identical (7 out of 8, the first one was off by a hair), and that's how I could show #31009 matches master exactly. I only tested the CUDA part, not Vulkan. Could you mark it ready so it gets review? |
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
thread timing causes a non-deterministic KLD (from 0.0004 to 0.011 between runs)
caught in the QSA indexer only for MoE fusions
Additional information
TBD, probably will file a bug - other backends has it too
Requirements