Inference › Optimization & Performance › Context / KV Cache v
prefix caching on repeated workflows with TensorRT-LLM

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
prefix caching on repeated workflows with TensorRT-LLM
amberplane Offline
Junior Member
**
Posts: 26
Threads: 4
Joined: Aug 2026
Reputation: 0
#11
10-19-2026, 05:18 AM
What exact setup are you running? Are you testing this on mini PC or something else?
Find
Reply
turboscope Offline
Junior Member
**
Posts: 35
Threads: 8
Joined: Aug 2026
Reputation: 0
#12
10-19-2026, 05:57 AM
Quote:What exact setup are you running? Is this local-only or are you routing anything externally?

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)