[Feature] is flex attention compatible?

[johnnynunez]

Checklist

• 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 2. Please use English, otherwise it will be closed.

Motivation

context:
In the future, we plan on extending this support to allow for quantized versions of attention or things like RadixAttention as well.

https://pytorch.org/blog/flexattention/

Related resources

No response

[zhaochenyang20]

hmmm. I personally do not know this. Maybe cc @yzh119