vmlx

by jjang-ai · MCP Server · ★ 521

About vmlx

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

anthropic-apikvcache-compressionkvcache-optimizationkvcache-reusellmlmstudiomacbookmcp-servermlxmlxllm

Quick Facts

Stars521
Forks64
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score34.75/100
Open Issues23
Last Updated2026-05-22
Created2026-02-18
Platformsmcp, python
Est. Tokens~3962k

Compatible Skills

These tools work well together with vmlx for enhanced workflows:

  • mlx-omni-server — semantic(0.35)+complementary+shared_fw(openai)+rare_topics+same_lang+shared_platform (60%)
  • snackcache — semantic(0.17)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (59%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is vmlx?

vmlx is vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!. It is categorized as a MCP Server with 521 GitHub stars.

What programming language is vmlx written in?

vmlx is primarily written in Python. It covers topics such as anthropic-api, kvcache-compression, kvcache-optimization.

How do I install or use vmlx?

You can find installation instructions and usage details in the vmlx GitHub repository at github.com/jjang-ai/vmlx. The project has 521 stars and 64 forks, indicating an active community.

What license does vmlx use?

vmlx is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse MCP Server tools