s-moe melasistema · COMPLETED
Model-agnostic inference engine for fine-grained Mixture-of-Experts LLMs on Apple Silicon — streams experts from NVMe so the model never has to fit in RAM (a 235B runs from 32 GB up). Designed with an AI agent across some sessions: the direction came from human curiosity, the implementation depth from the collaboration.
github.com/melasistema/s-moe · ★ 1 · Forks 0 · Size 1.6 MB
SUMMARY
Technologies 6
Scored 6
Observed 6
Practices 6
Evidence 6
Skips 0
COVERAGE
Analyzed 32 files · 92 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
C++ LANGUAGE Depth 70
16 files · PRODUCTION
Python LANGUAGE Depth 70
8 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 62
2 files · PRODUCTION
TypeScript LANGUAGE Depth 78
7 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-06-09
Last commit 2026-07-19
Active months 2
Commits 92