HN
Hacker News
Top
New
Best
Ask
Show
Jobs
gauravapiscean
57 karma · joined January 17, 2022
submissions
comments
Decode-Latency Feedback Prefill: A Model-Free Controller
arxiv.org
·
1 pts
·
gauravapiscean
·
1
LRU is harder to beat than the KV-cache papers suggest
github.com
·
108 pts
·
gauravapiscean
·
58