Inference › Inference Engines › TensorRT-LLM v
serving on Blackwell

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
serving on Blackwell
kernelmike Offline
Member
***
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation: 0
#5
10-14-2026, 09:20 PM
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Mostly CUDA, sometimes wrong, usually measured
Find
Reply


Messages In This Thread
serving on Blackwell - by torchtrack24 - 10-09-2026, 07:41 PM
Re: serving on Blackwell - by kernelmike - 10-11-2026, 07:42 PM
Re: serving on Blackwell - by tensorkite - 10-11-2026, 08:16 PM
Re: serving on Blackwell - by kernelpeak - 10-14-2026, 10:00 PM
Re: serving on Blackwell - by syshouse - 10-13-2026, 09:03 AM
Re: serving on Blackwell - by kernelmike - 10-14-2026, 09:20 PM
Re: serving on Blackwell - by kernelgrid - 10-14-2026, 11:10 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)