why did throughput drop after update: setup advice

[oxidemixer]

My first guess would be this: On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[deltapoint17]

Interesting, I hadn't tried that. The pattern around embeddings has been pretty similar for me. I got better results once I stopped chasing one metric

Maybe, but I had the opposite result. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere.

[nanogarden]

That matches what I was seeing. I ended up in about the same place using vLLM.