PCIe lane weirdness with inference loads

[cudahouse]

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 consumer GPUs.

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

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[vrambandit]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefix caching. Not glamorous advice, but repeatable baselines save a lot of time.

[dockkite69]

worth checking the driver first.

[sanevault]

Appreciate the detail. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[embersmith]

Appreciate the detail. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the

subscribed, curious where this lands.

[kernelhouse70]

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.

[vrambandit]

What exact setup are you running? Is this local-only or are you routing anything externally?

[quantsupply]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there.

[turbogrid11]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.

[mangopath4]

That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.