quant support gaps on GB200

[northcraft90]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[sysstation69]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

I'm happy to test one more variant if you want a second data point.

[kernelmike]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

Good point. 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.

[labline]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

What worked for me was pretty simple. If you're on SGLang, 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.

[kernelpeak]

What worked for me was pretty simple. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious.