vllm icon indicating copy to clipboard operation
vllm copied to clipboard

Support for longchat-7b-16k

Open yguo33 opened this issue 2 years ago • 0 comments

It would be great, if you can add support for longchat(from Fastchat) models, which have 16k context length:

https://github.com/lm-sys/FastChat

https://github.com/lm-sys/FastChat/blob/6d06351542bc0c3701d54619e6df4c26aa91a260/fastchat/model/llama_condense_monkey_patch.py#L10C18-L10C18

yguo33 avatar Jul 04 '23 10:07 yguo33