+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: PyTorch / JAX / Other Frameworks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=34)
+--- Thread: JAX for inference only on dual 3090 (/showthread.php?tid=1121)
Pages:
1
2
Re: JAX for inference only on dual 3090 - quiettoken - 10-14-2026
Appreciate the detail. 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.
Re: JAX for inference only on dual 3090 - latentpeak22 - 10-16-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: JAX for inference only on dual 3090 - deltapoint17 - 10-16-2026
Not sure I agree there. I've seen people blame token cost when the real issue was much more mundane.
Re: JAX for inference only on dual 3090 - torchshed - 10-17-2026
same here on my side.
Re: JAX for inference only on dual 3090 - vramghost - 10-17-2026
Interesting, I hadn't tried that. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
I'm happy to test one more variant if you want a second data point.