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
northcraft90 Offline
Member
***
Posts: 63
Threads: 7
Joined: Sep 2026
Reputation: 0
#1
09-23-2026, 01:41 AM
Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: vLLM on Threadripper box, keeping HBM constraints in mind from the start.

If someone wants the exact settings I can clean them up and post them.

This is mostly for local work rather than public serving.
Find
Reply


Messages In This Thread
serving on Blackwell - by northcraft90 - 09-23-2026, 01:41 AM
Re: serving on Blackwell - by batchcraft - 09-23-2026, 02:55 AM
Re: serving on Blackwell - by torchtrack24 - 09-23-2026, 04:14 AM
Re: serving on Blackwell - by batchcraft - 09-24-2026, 05:03 PM
Re: serving on Blackwell - by routecrate - 09-24-2026, 05:45 PM
Re: serving on Blackwell - by tensorriver - 09-24-2026, 06:33 PM
Re: serving on Blackwell - by northcraft90 - 09-25-2026, 07:22 AM
Re: serving on Blackwell - by kernelmike - 09-25-2026, 08:07 AM
Re: serving on Blackwell - by quiettoken - 09-26-2026, 08:13 AM
Re: serving on Blackwell - by kernelmike - 09-26-2026, 09:17 AM
Re: serving on Blackwell - by northcraft90 - 09-26-2026, 10:16 AM
Re: serving on Blackwell - by syshouse - 09-26-2026, 12:54 PM
Re: serving on Blackwell - by kernelgrid - 09-26-2026, 03:29 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)