prompt length getting silly

[paperport64]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

Good point. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[rasterhall]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

worth checking the driver first.

[batchember]

That matches what I was seeing. That matches what I saw on 7900 XTX.

[quiettoken]

That matches what I was seeing. That matches what I saw on 7900 XTX.

What worked for me was pretty simple. If you're on TensorRT-LLM, 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.

[mintstation99]

That matches what I was seeing. That matches what I saw on 7900 XTX.

Thanks, that helps. The pattern around small local stacks has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[localpatch]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.