xiangqi1997
xiangqi1997
see https://github.com/buyizhiyou/NRVQA/blob/master/brisque.py#L123 your "extract_brisque_feats" function used on a low resolution image, not mscn coefficients, maybe this big problem caused "brisque score" always equal to 0.49
### Motivation Very impressive work, noticed that a recent PR supported internvl-chat-v1.5, but it was not realistic to run on two 24G GPU cards. May I ask when will quantification...
Wondering if streaming output is supported? Or are there any results about the time to first token and time per output token? Thanks.