David-Lee-1990

is baichuan-gptq supported?

> Hello, the question seems to remain unsolved. When I set max_num_batched_tokens very big (such as 10000) or the length of input tokens is quite long (near 10000), vLLM will...

链接：https://pan.baidu.com/s/13tiZ7Kz6xr4eQ4Fsb-I1oA 提取码：3gp9 github上的版本是简单版本，给您带来不便，很抱歉。 抱歉，时间比较久了，您可以看一下我在百度网盘上存储的版本。代码在code目录下，还有一份ppt在 PRA学习总结目录下。 paths_threshold.txt是加了 query support限制后的结果。 (1. Sorry for submitting a incomplete version of code; 2. for a complete version, please download it from Baidu Disk: https://pan.baidu.com/s/13tiZ7Kz6xr4eQ4Fsb-I1oA password:3gp9...