Skip to content

chore: bump mlx-swift-lm for TurboKV (#175) and QAT assistant fixes - #191

Merged
solderzzc merged 1 commit into
mainfrom
chore/bump-mlx-swift-lm-turbokv-qat
Sep 25, 2026
Merged

solderzzc merged 1 commit into
mainfrom
chore/bump-mlx-swift-lm-turbokv-qat

Conversation

@solderzzc

Copy link
Copy Markdown
Member

Bumps mlx-swift-lm to SharpAI/mlx-swift-lm main (7cc37a0), which adds:

README: the #175 warning becomes a "fixed" note (with the speed cost), and the QAT assistant known issue is replaced with a "now works" note. The #184 --mtp warning stays until that fix lands.

Merge this before #190, so the first release cut after #190 includes these fixes.

AI usage: written with Claude Code (Opus 5.5); the maintainer reviews before merge.

🤖 Generated with Claude Code

Picks up SharpAI/mlx-swift-lm#65 (TurboKV keeps compressed history in
attention, #175) and #66 (QAT Gemma 4 assistants). Updates the README
known issues.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@solderzzc
solderzzc merged commit b0d15fb into main Sep 25, 2026
14 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.

--turbo-kv loses context history after 2K tokens (attention sees only the last 256 tokens)

1 participant