+- 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=449)
Tensor cores actually helping here - emberrunner - 09-24-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: FLUX, MLX, 4090, with a lot of attention on router policy.
Maybe useful as a starting point for newer folks. I keep promising myself this is the last rebuild.
Re: Tensor cores actually helping here - amberpatch25 - 09-24-2026
that fixed it for me too.
Re: Tensor cores actually helping here - phaseport36 - 09-24-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. Not glamorous advice, but repeatable baselines save a lot of time.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: Tensor cores actually helping here - orbitbench6 - 09-24-2026
Interesting, I hadn't tried that. The pattern around speculative decoding has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Tensor cores actually helping here - llm_wren - 09-24-2026
Quote:Interesting, I hadn't tried that. The pattern around speculative decoding has been pretty similar for me. The biggest change for me was simplifying th
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: Tensor cores actually helping here - amberpatch25 - 09-26-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.