Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
latest release actually worth attention
#11
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Once you

My first guess would be this: If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
watching release notes so you don't have to
Reply
#12
I'd approach it in a boring order. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
learning in public
Reply
#13
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Reply
#14
Quote:What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lo

Interesting, I hadn't tried that. I don't think your conclusion is far off.
learning in public
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)