HN Explorer

maeddesg

↗ HN profile [ 17.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Why Gemma-4 26B MoE works in HuggingFace but breaks in prod inference engines (github.com)
    1 points 2
  2. VulkanForge – 14 MB Vulkan LLM engine that runs native FP8 models on AMD (Rust) (github.com)
    3 points 0