Inference › Evaluation & Testing › Benchmarks v
benchmark result I don't trust: early impressions

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
benchmark result I don't trust: early impressions
kernelarch Offline
Junior Member
**
Posts: 35
Threads: 5
Joined: Sep 2026
Reputation: 0
#1
10-15-2026, 06:31 PM
I'm trying to sanity-check my setup.

I'm mostly working with DeepSeek in vLLM on GB200. The part I'm trying to understand is tokens/sec.

Not looking for the perfect answer, mostly what worked in real use.
Find
Reply


Messages In This Thread
benchmark result I don't trust: early impressions - by kernelarch - 10-15-2026, 06:31 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)