multi-GPU offload advice for DeepSeek

[visionyard23]

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

I tried this with Mixtral using MLX on B200. The headline result was better than I expected, but prefill/decode split still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.

I care more about stability than squeezing the last possible tokens/sec out of it.

If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.

[mellowwire98]

Thanks, that helps. I ended up in about the same place using SGLang.

[modrunner27]

I don't think that's the whole story. I get why that seems right, but on mini PC the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.