HN Explorer

quatonion

↗ HN profile [ 59.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Valkyr LM Inference with Realtime Guarantees (github.com)

    Valkyr is a fresh take on LM Inference runtimes. It's quite different from llama.cpp, vLLM, or ZINC for example. Written in Zig, and super clean, with no dependencies apart from Vulkan Compute itself of course. While it…

    3 points 0
  2. Galton Board Softmax O(N2) Replacement (github.com)
    1 points 1