Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
TensorRT-LLM worth the setup time: early impressions
#2
That matches what I was seeing. I ended up in about the same place using SGLang. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Mostly CUDA, sometimes wrong, usually measured
Reply


Messages In This Thread
Re: TensorRT-LLM worth the setup time: early impressions - by kernelmike - 10-06-2026, 04:40 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)