NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
Nvidia Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context (developer.nvidia.com)
2001zhaozhao 1 days ago [-]
Gemma 31B dense at 3k TPS seems like a pretty big deal. Groq has always been more efficient than Cerebras at running very small models and this release seems to be no exception.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 23:19:53 GMT+0000 (Coordinated Universal Time) with Vercel.