+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: tokens/sec tuning ideas with TensorRT-LLM (/showthread.php?tid=799)
Pages:
1
2
Re: tokens/sec tuning ideas with TensorRT-LLM - routeforge64 - 10-14-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling.