serving on Blackwell

[northcraft90]

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.

[syshouse]

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.

[kernelgrid]

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.