If you want the fastest open source implementation on Blackwell and AMD MI355, check out Modular's MAX nightly. You can pip install it super fast, check it out here: https://www.modular.com/blog/day-zero-launch-fastest-perform...

-Chris Lattner (yes, affiliated with Modular :-)

▲

nabakin 2 days ago | parent | next [-]

Faster than TensorRT-LLM on Blackwell? Or do you not consider TensorRT-LLM open source because some dependencies are closed source?

▲

melodyogonna 2 days ago | parent [-]

I reviewed the TensorRT-LLM commit history from the past few days and couldn't find any updates regarding Gemma 4 support. By contrast, here is the reference for MAX:https://github.com/modular/modular/commit/57728b23befed8f3b4...

▲

nabakin 2 days ago | parent [-]

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 2 days ago | parent [-]

How is the sglang performance on Blackwell for this model?

	▲	nabakin 2 days ago \| parent [-]
		Dunno but there's a PR for it. Probably also more performant than Modular.

▲

jjcm 2 days ago | parent | prev [-]

What % of a speedup should I be expecting vs just running this the standard pytorch approach?