+- 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=1489)
Re: Tensor cores actually helping here - thetapath - 10-18-2026
worth checking the driver first.
Re: Tensor cores actually helping here - edgecoast - 10-18-2026
Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Tensor cores actually helping here - dockember - 10-18-2026
I'd approach it in a boring order. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Tensor cores actually helping here - orbitbench6 - 10-18-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
I'm especially interested in mistakes worth avoiding.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: Tensor cores actually helping here - amberpatch25 - 10-19-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: Tensor cores actually helping here - edgecoast - 10-19-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: Tensor cores actually helping here - thetapath - 10-19-2026
My first guess would be this: On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: Tensor cores actually helping here - amberpatch25 - 10-19-2026
I hit almost the same issue last night.