Back to trending
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
Python500 stars60 forksApache-2.0
anthropic-apikvcache-compressionkvcache-optimizationkvcache-reusellmlmstudiomacbookmcp-servermlxmlxllmmlxstudioomlxomlx-alternativeopenai-apiopenclawopenclaw-agentpersistent-memoryprefix-cachevmlx
Rankings
Daily
#7276
0
Weekly
#13032
0
Monthly
#5595
0
Engagement
Total stars
Daily new stars
Get badge
This repository is tracked by Trending Repos. The badge upgrades automatically if it ever cracks the top 100.
Markdown
HTML
<img src="https://trending-repos.com/badge/jjang-ai/vmlx.svg" alt="Trending Repos" />Raw URL
https://trending-repos.com/badge/jjang-ai/vmlx.svg