paged attention observations with TensorRT-LLM

[relaynest82]

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 token cost.

Wondering if this is just where the whole space is heading now.

[cacheline]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.