OLMoE Replication - #1270
Merged
Merged
Conversation
dlwh
approved these changes
May 14, 2025
ryan-williams
pushed a commit
that referenced
this pull request
Oct 31, 2025
A stripped down version of #1270 . This leaves the existing decoding as is, but to avoid the issues we've been seeing with page management, it simply resets the engine state between request batches. In theory this removes the risk of memory leaks across batches or mis-allocations - if one batch works than all subsequent batches should work as well.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Fixes #1183
Replicate OLMoE experiments to show performance gains going from dense model to similar sized moe model.