Yixin Dong
Yixin Dong
@Jimmy-L99 Do you still have any issue with it? If so, feel free to provide the reproducing steps and we can figure it out.
@Muqi1029 Thanks for proposing this feature! It's reasonable for LLMs to provide fields in any order they want. However it could be hard to describe any order in BNF. Its...
Thanks @Seven-Streams for explanation. Here I think XGrammar should only allow tokens starting with `\"`, including `\",` and more, and 2869(`Se`) or 30161(`Seattle`) should be masked. So it should have...
Closed. Feel free to reopen it if the problem still occurs.
Hi @denadai2 , thanks for reporting this issue! Sorry for the late response because I was occupied with some paper-related work. Your output still seems to be valid JSON, but...
It looks good to me. Supporting AMD GPUs is very meaningful. Thanks, and I am supportive of merging it!
@divakar-amd @micah-wil I have merged it. Thanks for the contribution!
Hi @gryffindor-rr, thanks for asking about that. Currently, the min and max integer range is supported (we are enhancing it in #182 to better support negative integer range). The num...
We will sync with vLLM team to enable more features of json schema with XGrammar backend.
Hi @gryffindor-rr, thanks for asking about the C++ API! XGrammar's Python API is a simple wrapper around the C++ API, so you can refer to our [Python documentation](https://xgrammar.mlc.ai/docs/api/python/index.html) to learn...