Used A6000 worth it now

[phaseshed]

Did a bit of testing and thought I'd post the result here.

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around tail latency.

Curious if anyone else landed in the same place.

[embersmith]

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

[rocmriley]

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

Thanks, that helps. 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.

[cudapoint]

That matches what I was seeing. 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 worked for me was pretty simple. If you're on MLX, 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.

[fusedhall]

Appreciate the detail. 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.

[batchwire]

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

[rocmriley]

Interesting, I hadn't tried that. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[fusedriver]

What worked for me was pretty simple. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.

[batchember]

I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.