T To Play Claw Browse tools
Back to Tools
workflow ยท tool profile

vmlx

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

mcp
01

At a glance.

A compact read before the deeper capability notes and official setup links.

Fit snapshot
Format WORKFLOW
Category mcp
Review official docs
02

Core features.

Feature cards focus on what the tool helps users do, not generated setup commands.

01

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

02

Topics: anthropic-api, kvcache-compression, kvcache-optimization, kvcache-reuse, llm

03

GitHub stars: 701

04

Last pushed: 2026-06-19

04

Agent / Skill / MCP / Workflow fit.

This panel keeps technical format separate from the user-facing AI category.

Tool type WORKFLOW
Use categories mcp
Works with Review official docs
05

Official setup path.

Generated install snippets are intentionally not mirrored here because they drift. The page links to source-owned setup docs instead.

source Official source github GitHub docs Docs / README quickstart Quick start releases Releases
06

Evidence and adoption notes.

These notes help a user decide whether to investigate the official project further.

Source repository last pushed at 2026-06-19T04:08:37Z.

Generated from source metadata; confirm operational details in the official project before adopting it.

Review the upstream license, maintenance activity, and issue history before using it in production.

Trusted source

Trace the origin before adopting.

source https://github.com/jjang-ai/vmlx