new here, what's your stack

[tensorkite]

Can you fill in a bit more context? Are you testing this on Threadripper box or something else?

[cacheplane98]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.

[plaingarden18]

Appreciate the detail. That matches what I saw on mini PC.

[ggufwire22]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at batch size. Once you know the plain path works, then add the faster path back in piece by piece.

[tensorkite]

Thanks, that helps. I don't think your conclusion is far off.