Inference › Drivers / Frameworks / Toolkits › PyTorch / JAX / Other Frameworks v
JAX for inference only on 4090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
JAX for inference only on 4090
embersmith Offline
Junior Member
**
Posts: 23
Threads: 3
Joined: Aug 2026
Reputation: 0
#11
09-30-2026, 09:06 PM
Need a little more detail here. Is this local-only or are you routing anything externally?
VRAM first, aesthetics later
Find
Reply
visionyard23 Offline
Member
***
Posts: 55
Threads: 8
Joined: Sep 2026
Reputation: 0
#12
09-30-2026, 09:44 PM
Quote:Need a little more detail here. Is this local-only or are you routing anything externally?

My first guess would be this: On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Apple Silicon • MLX mostly
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)