Inference › Optimization & Performance › Context / KV Cache v
draft model choices for Phi

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
draft model choices for Phi
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#10
09-18-2026, 08:45 AM
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints. Not glamorous advice, but repeatable baselines save a lot of time.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
draft model choices for Phi - by cacheline - 09-09-2026, 03:21 AM
Re: draft model choices for Phi - by fastfield4 - 09-11-2026, 03:49 AM
Re: draft model choices for Phi - by vramarch - 09-11-2026, 04:47 AM
Re: draft model choices for Phi - by cacheline - 09-11-2026, 04:22 AM
Re: draft model choices for Phi - by cacheline - 09-12-2026, 05:23 AM
Re: draft model choices for Phi - by cacheline - 09-12-2026, 07:10 AM
Re: draft model choices for Phi - by promptpoint - 09-15-2026, 07:50 AM
Re: draft model choices for Phi - by amberrunner - 09-15-2026, 08:24 AM
Re: draft model choices for Phi - by cacheline - 09-18-2026, 08:45 AM
Re: draft model choices for Phi - by visionforge - 09-18-2026, 09:25 AM
Re: draft model choices for Phi - by cacheline - 09-18-2026, 11:03 AM
Re: draft model choices for Phi - by amberrunner - 09-18-2026, 03:30 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)