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
visionforge Offline
Member
***
Posts: 121
Threads: 15
Joined: Sep 2026
Reputation: 0
#3
10-18-2026, 12:55 PM
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
image models by night, local pipelines by day
Find
Reply


Messages In This Thread
serving on Blackwell - by kernelmike - 10-17-2026, 11:39 PM
Re: serving on Blackwell - by localpatch - 10-18-2026, 12:23 PM
Re: serving on Blackwell - by visionforge - 10-18-2026, 12:55 PM
Re: serving on Blackwell - by routecrate - 10-18-2026, 04:49 PM
Re: serving on Blackwell - by kernelgrid - 10-18-2026, 01:33 PM
Re: serving on Blackwell - by kernelmike - 10-18-2026, 02:09 PM
Re: serving on Blackwell - by audioforge - 10-18-2026, 05:26 PM
Re: serving on Blackwell - by rasterbench - 10-18-2026, 06:46 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)