CUDA update broke my throughput with TensorRT-LLM

[latentgarden]

Thanks, that helps. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[phaseport36]

Did a small comparison this afternoon. On A6000 with llama.cpp, I saw basically the same behavior. The main thing that moved was latency, not quality.

I'm happy to test one more variant if you want a second data point.