non-AI thing you built recently

[routecraft]

Need a little more detail here. What model, what runtime, and roughly what context size?

following this because I'm in the same boat.

[cobaltlab]

Appreciate the detail. I don't think your conclusion is far off.

[tinycontext]

Appreciate the detail. I don't think your conclusion is far off.

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at batch size. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

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

[thetapath]

worth checking the driver first.

[northcraft90]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Not glamorous advice, but repeatable baselines save a lot of time.