Skip to content

fix(miniswen): improve cache hit rate for Meta Muse models - #11

Merged
baygeldin merged 1 commit into
mainfrom
fix/muse-caching
Oct 14, 2026
Merged

baygeldin merged 1 commit into
mainfrom
fix/muse-caching

Conversation

@baygeldin

@baygeldin baygeldin commented Oct 14, 2026 •

Copy link
Copy Markdown
Collaborator

Meta Muse needs prompt_cache_key to increase cache hit rate:
https://dev.meta.ai/docs/prompt-caching#prompt-cache-key

This PR adds a stable cache key to each run. The key is reused if a run fails and needs to be restarted.

@baygeldin
baygeldin marked this pull request as draft October 14, 2026 16:12
@baygeldin
baygeldin marked this pull request as ready for review October 14, 2026 16:36
@baygeldin
baygeldin requested a review from palkan October 14, 2026 16:36
@baygeldin
baygeldin merged commit ede53b2 into main Oct 14, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants