working config for 32k context with SGLang

[sparrowhall]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with prefill/decode split.

Maybe obvious to some of you, but it clicked for me this week.

[kernelgrid]

Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[rocmriley]

following this because I'm in the same boat.

[rasterbench]

I'd approach it in a boring order. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[vramstream]

I'd approach it in a boring order. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.

[mangoquill]

A couple things I'd check first. On 7900 XTX, 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.

[cachebench]

I'd approach it in a boring order. 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.