HN Explorer

snyhlxde

↗ HN profile [ 71.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. JetSpec Enables Up to 9.64x Lossless LLM Inference Speedup with Up to 1000TPS (haoailab.com)
    4 points 1
  2. 1 points 0
  3. 5 points 0
  4. 2 points 0
  5. 1 points 0
  6. 1 points 0
  7. 1 points 0
  8. 1 points 0
  9. Claude-3.7 outperforms other models in realtime Super Mario Bros (x.com)
    3 points 1
  10. Evaluating LLM Reasoning Through Live Computer Games (lmgame.org)
    24 points 14
  11. CLLMs: LLMs can be taught to parallel decode with up to 3.5x speedup (twitter.com)
    3 points 0
  12. Transforming LLMs into parallel decoders boosts inference speed by up to 3.5x (hao-ai-lab.github.io)
    7 points 0