throughput per watt reality check

[kernelmike]

Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around PyTorch and 4090.

Would rather learn from your scars than collect my own all at once.

This is mostly for local work rather than public serving. The logs were somehow calmer than I was.

[rocmpath]

Not sure I agree there. I've seen people blame KV cache pressure when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[thetashed24]

Appreciate the detail. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[dockkite69]

My first guess would be this: If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[oxidegrove40]

I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[dockworks23]

I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[latentcraft]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[promptfield]

I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[torchsmith25]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[visionforge]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.