rreinold/jev-serve

Single logit inference runtime for all LLM models

2 best points · 2 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• Jev-serve: Run latest qwen3.8, all LLM models, mlx-supported (2 points, 2 comments, by rreinold2, 2026-09-23)