Profile Picture
  • All
  • Search
  • Images
  • Videos
  • Maps
  • News
  • Copilot
  • More
    • Shopping
    • Flights
    • Travel
  • Notebook
  • Top stories
  • Sports
  • U.S.
  • Local
  • World
  • Science
  • Technology
  • Entertainment
  • Business
  • More
    Politics
Order byBest matchMost fresh
  • Past 24 hours
    • Any time
    • Past hour
    • Past 7 days
    • Past 30 days
GitHub
15h

40x Faster AI Inference with FP16/INT8 Quantization & Multi-GPU Support

Llama 3.2 ONNX+TRT 45ms/token 8GB ...

Some results have been hidden because they may be inaccessible to you

Show inaccessible results

Trending now

Allows CA to use new map
Launches new campaign
To receive Medal of Honor
Suspect charged w/ terrorism
PR voting machines probed?
Cuba willing to talk to US
Rejects DOJ interview request
Recalls 450K+ vehicles
To resume military talks
NYC joins UN health network
Man threatening ICE charged
Fatal car crash in LA
JD Vance arrives in Milan
Drops out of LA mayor’s race
Bad Bunny on Super Bowl
NCAA denies appeal
TX anti-ESG law blocked
Alex Saab arrested
Apologizes to Epstein victims
Bans e-waste imports
US-RU nuclear pact expires
Charged with felony assault
AZ helicopter crash kills 2
Postpones Las Vegas shows
Search enters 5th day
Nationwide recall expanded
Famine spreads in Sudan
US job openings fall
Abandon merger talks
Paul Weiss chairman resigns
Peace talks continue
Montana's Hauck retires
DOJ removes ICE lawyer
  • Privacy
  • Terms