when TensorRT-LLM clearly wins: early impressions

[vectorport]

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

[kernelmike]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[vramport]

Maybe, but I had the opposite result. I get why that seems right, but on B200 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.