JustVugg/
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
by Vincenzo Fornaro C Apache-2.0 licence 5,883 forks Created Jul 2026 View on GitHub
- Stars
- 49,964
- 98% of JustVugg's stars
- Rank
- #540
- of 852,369 repos, top 0.06%
- Up 36 places this week
- In C
- #10
- of 32,714 repos, top 0.03%
Among 852,369 repos
40k–63k stars: 415 repos, including colibri
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +34 stars to reach #539
- Next milestone
- +82,253 stars to reach the top 0.01%
- Popular
- One of 5,755 repos with 10k+ stars