[nabakin]

If OP meant they have the fastest implementation of Gemma 4 on Blackwell at the moment, I guess that is technically true. I doubt that will hold up when TensorRT-LLM finishes their implementation though.

[pama]

How is the sglang performance on Blackwell for this model?

[nabakin]

Dunno but there's a PR for it. Probably also more performant than Modular.