Used A6000 worth it now

[dockkite69]

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

I tried this with Mistral using PyTorch on B200. The headline result was better than I expected, but speculative decoding still ended up being the limiting factor.

Curious if anyone else landed in the same place.

[vrambandit]

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

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece. The logs were somehow calmer than I was.

[batchember]

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

[signaltrack44]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.

[cudapoint]

A couple things I'd check first. If you're on LM Studio, 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.

[batchwire]

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives.