+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: Tensor cores actually helping here (/showthread.php?tid=1419)
Tensor cores actually helping here - kernelmike - 10-17-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: TensorRT-LLM on Threadripper box, keeping HBM constraints in mind from the start.
Maybe useful as a starting point for newer folks.
Re: Tensor cores actually helping here - orbitbench6 - 10-18-2026
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.