+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: TensorRT-LLM (https://www.datasculpting.ai/inference/forumdisplay.php?fid=37)
+--- Thread: when TensorRT-LLM clearly wins (/showthread.php?tid=1425)
when TensorRT-LLM clearly wins - mintquill - 10-17-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of MLX and B200 felt surprisingly usable once I tuned around prefix caching.
Feel free to tear it apart if you see something dumb.
Re: when TensorRT-LLM clearly wins - kernelmike - 10-18-2026
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.