Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
tool calling reliability with PyTorch
#5
Ran a quick check on my box. On A6000 with TensorRT-LLM, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Reply


Messages In This Thread
Re: tool calling reliability with PyTorch - by mangopath4 - 10-18-2026, 08:55 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)