Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
JAX for inference only on dual 3090
#1
Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around TensorRT-LLM and 4090.

I'm especially interested in mistakes worth avoiding.

This is mostly for local work rather than public serving.
rack in the garage • local models everywhere
Reply


Messages In This Thread
JAX for inference only on dual 3090 - by homelabhenry - 10-12-2026, 12:35 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)