Tenosra/Proxima

Proxima lets existing GPUs serve 4x more concurrent requests

3 best points · 1 comments · 1 Hacker News post · 26 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Proxima serves 4x more requests with no hardware change on vLLM (3 points, 1 comments, by pythongiant, 2026-08-11)