Zhu Wei

@mrwyattii , will you add support Mixtral with the old inference interface in the future ? as it's quite a popular model.

Hi, @ip2016，[PR fix](https://github.com/intel/intel-extension-for-tensorflow/commit/740b59c563e265110531d2406206ef0914075d81) for this NAN issue has been merge, please follow doc [here](https://github.com/intel/intel-extension-for-tensorflow/blob/main/docs/install/how_to_build.md) to rebuild and have a try.

> Thanks for this contribution! What happens if user calls a function that's not currently supported (e.g. paged KV or varlen)? Currently, all checks are handled on the kernel side,...

hi, @jfedorov , i also run into this issue, and i updated to latest commit(9ee0e46cafa145856eaeeefe5f26ec046462300f), below is the error info, is it expected? ``` pti-gpu/tools/oneprof/metric_query_cache.h:69: _zet_metric_query_handle_t* MetricQueryCache::GetQ uery(ze_context_handle_t): Assertion `status...