Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
multimodal local stack that feels real
#11
Appreciate the detail. The pattern around long context has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
image models by night, local pipelines by day
Reply
#12
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Reply
#13
What exact setup are you running? Are you testing this on 7900 XTX or something else?
Reply
#14
I tested this tonight. On GB200 with TensorRT-LLM, I saw basically the same behavior. I expected the model choice to matter more than it did.
Reply
#15
Quote:Did a small comparison this afternoon. On B200 with SGLang, I saw basically the same behavior.

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Reply
#16
Did a small comparison this afternoon. On B200 with SGLang, I saw basically the same behavior.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)