Scottcjn/
LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of...
by AutoJanitor Python AGPL-3.0 licence 59 forks Created Jan 2026 View on GitHub
- Stars
- 174
- 2% of Scottcjn's stars
- Rank
- #310,886
- of 851,984 repos, top 37%
- In Python
- #60,795
- of 173,300 repos, top 36%
Among 851,984 repos
160–250 stars: 104,058 repos, including ram-coffers
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
- +1 star to reach #309,421
- Next milestone
- +47 stars to reach the top 30%
- Popular
- One of 490,652 repos with 100+ stars