HN Explorer

NicoConstant

↗ HN profile [ 16.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Real-time LLM Inference on Standard GPUs: 3k tokens/s per request (blog.kog.ai)
    219 points 38
  2. Kog AI – Building a Real-Time Inference Stack on AMD Instinct GPUs [video] (youtube.com)
    8 points 0