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
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#11
10-14-2026, 03:20 PM
following this because I'm in the same boat.
measure twice, benchmark three times
Find
Reply
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#12
10-15-2026, 03:24 PM
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
measure twice, benchmark three times
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)