password162156/hexcore-llm

Zero-Trust, Ultra-Low Latency Paged KV Cache Allocator for LLM Inference (C++20 / CUDA / Python)

2 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• HexCore: Low-Latency Paged KV Cache Allocator in C++20 and CUDA (2 points, 0 comments, by XXXGhost, 2026-07-31)