Inference › Evaluation & Testing › Benchmarks v
eval setup for local models for Kimi

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
eval setup for local models for Kimi
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#8
09-30-2026, 09:21 PM
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
Re: eval setup for local models for Kimi - by cacheline - 09-30-2026, 09:21 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)