Skip to content

docs: add TurboQuant MLX PDD plan#2148

Open
ianleon wants to merge 1 commit into
exo-explore:mainfrom
ianleon:plan/turboquant-mlx-pdd
Open

docs: add TurboQuant MLX PDD plan#2148
ianleon wants to merge 1 commit into
exo-explore:mainfrom
ianleon:plan/turboquant-mlx-pdd

Conversation

@ianleon

@ianleon ianleon commented Jun 4, 2026

Copy link
Copy Markdown

Summary

  • add a design plan for TurboQuant-style KV cache compression in the MLX runner
  • outline phased work for benchmarking, cache adapter integration, Apple Silicon fast path, and PDD cache handoff
  • call out Qwen3-Next hybrid cache handling and default-off rollout constraints

Tests

  • not run; documentation-only change

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.

1 participant