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
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#7
10-19-2026, 04:03 AM
Quote:[quote]That matches what I was seeing. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumpt

I hit almost the same issue last night.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
paged attention observations - by cacheline - 10-18-2026, 02:16 AM
Re: paged attention observations - by edgecoast - 10-18-2026, 06:02 PM
Re: paged attention observations - by cacheline - 10-19-2026, 12:00 AM
Re: paged attention observations - by dockkite69 - 10-18-2026, 07:34 PM
Re: paged attention observations - by cacheline - 10-18-2026, 08:50 PM
Re: paged attention observations - by sanepeak48 - 10-18-2026, 10:19 PM
Re: paged attention observations - by cacheline - 10-19-2026, 04:03 AM
Re: paged attention observations - by quantnest - 10-19-2026, 04:41 AM
Re: paged attention observations - by cacheline - 10-19-2026, 05:31 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)