Prefill/Decode split to run on heterogeneous hardware, and the transmission bottleneck of the KV cache was actually tackled by Kimi's mixed modeling.

View Original
Original content no longer visible
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments