+- 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: serving on Blackwell (/showthread.php?tid=414)
Pages:
1
2
Re: serving on Blackwell - northcraft90 - 09-26-2026
Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: serving on Blackwell - syshouse - 09-26-2026
Quote:Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the
I don't think that's the whole story. I've seen people blame speculative decoding when the real issue was much more mundane.
Re: serving on Blackwell - kernelgrid - 09-26-2026
Interesting, I hadn't tried that. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.