Inference › Optimization & Performance › Context / KV Cache v
paged attention observations

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
paged attention observations
oxidemixer Offline
Member
***
Posts: 50
Threads: 6
Joined: Sep 2026
Reputation: 0
#9
10-05-2026, 04:29 AM
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Find
Reply


Messages In This Thread
paged attention observations - by cobalttinker - 09-29-2026, 02:56 PM
Re: paged attention observations - by cacheline - 09-30-2026, 03:29 AM
Re: paged attention observations - by dockriver - 10-01-2026, 04:14 AM
Re: paged attention observations - by cacheline - 10-01-2026, 04:50 PM
Re: paged attention observations - by visionforge - 10-01-2026, 05:08 PM
Re: paged attention observations - by cacheline - 10-01-2026, 06:40 PM
Re: paged attention observations - by cacheline - 10-01-2026, 08:17 PM
Re: paged attention observations - by circuitkite - 10-02-2026, 04:21 AM
Re: paged attention observations - by oxidemixer - 10-05-2026, 04:29 AM
Re: paged attention observations - by cacheline - 10-05-2026, 05:35 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)