+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: Instinct pricing thoughts with TensorRT-LLM (/showthread.php?tid=505)
Pages:
1
2
Re: Instinct pricing thoughts with TensorRT-LLM - dockworks23 - 10-08-2026
I'd start with the simpler stack.
Re: Instinct pricing thoughts with TensorRT-LLM - mangohouse - 10-08-2026
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Instinct pricing thoughts with TensorRT-LLM - batchscope72 - 10-09-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?