HN Explorer

om8

↗ HN profile [ 66.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: HIGGS – new sota data-free LLM quantization (huggingface.co)

    My colleagues and I wrote a paper and integrated it into transformers. It has more of both accuracy and speed than NF4 We have compressed hf models for everyone to try:…

    2 points 0
  2. Show HN: Llama 3.1 8B CPU Inference in a Browser via WebAssembly (galqiwi.github.io)
    4 points 4