VeloGB10 – A GB10-specific inference engine
1 points by colingauvin 6 hours ago | 1 comments
  • colingauvin 6 hours ago |
    Not my project but wanted to share. My 2x Spark config with Qwen 3.8 Flash went from 37 tps to ~90 tps (prose). It's running phenomenally well and really impressive.