Inference › Inference Engines › Other Engines v
prefill bottlenecks on longer prompts

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
prefill bottlenecks on longer prompts
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#2
09-25-2026, 05:25 AM
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.

I hit almost the same issue last night.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: prefill bottlenecks on longer prompts - by vrambandit - 09-25-2026, 05:25 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)