Open
Conversation
Two fixes: 1. cache_wrapper.py: Added fallback when cache layers don't expose `offset` attribute 2. batched_model_kit.py: Separated cross-prompt cache key from live cache key The main issue was that batched models (like GPT-OSS) were tracking generated tokens in the cross-prompt cache key, preventing cache hits for new prompts with overlapping content.
|
All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
github-actions
bot
added
the
CLA signed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes lmstudio-ai/lmstudio-bug-tracker#1697
Fixed prompt caching for GPT-OSS 20B MLX models.
Two fixes:
offsetattributeThe main issue was that batched models (like GPT-OSS) were tracking generated tokens in the cross-prompt cache key, preventing cache hits for new prompts with overlapping content.
Testing:
~/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@20/lib/python3.11/site-packages/mlx_engine/with the updated file)