| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Download Repo ZIP] [Original HTTPS Page] |
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
No bs theatricals. Real automated pentesting. Mac only.
GLM-5.2 744B on 4x NVIDIA DGX Spark (GB10): measured vLLM TP=4 serving recipe, GB10 operational notes, and a single-API tool-plane backend
Add a description, image, and links to the vmlx topic page so that developers can more easily learn about it.
To associate your repository with the vmlx topic, visit your repo's landing page and select "manage topics."
| Back | FazBrowse Home | New Git URL |