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

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
draft model choices
vramport Offline
Junior Member
**
Posts: 45
Threads: 6
Joined: Aug 2026
Reputation: 0
#4
10-15-2026, 06:38 AM
A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
mostly local
Find
Reply


Messages In This Thread
draft model choices - by cacheline - 10-13-2026, 01:57 PM
Re: draft model choices - by promptpoint - 10-13-2026, 06:06 PM
Re: draft model choices - by cacheline - 10-14-2026, 06:34 AM
Re: draft model choices - by vramport - 10-15-2026, 06:38 AM
Re: draft model choices - by cacheline - 10-15-2026, 07:49 AM
Re: draft model choices - by audioforge - 10-17-2026, 05:20 PM
Re: draft model choices - by llm_wren - 10-15-2026, 08:03 PM
Re: draft model choices - by sparrowcraft - 10-18-2026, 08:35 PM
Re: draft model choices - by cacheline - 10-17-2026, 08:35 AM
Re: draft model choices - by cacheline - 10-17-2026, 06:13 PM
Re: draft model choices - by plainworks - 10-18-2026, 05:56 PM
Re: draft model choices - by cacheline - 10-18-2026, 06:11 PM
Re: draft model choices - by northhall88 - 10-18-2026, 06:26 PM
Re: draft model choices - by cacheline - 10-18-2026, 06:51 PM
Re: draft model choices - by vectorshed43 - 10-18-2026, 08:14 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)