Yu Liu
 The beg-vl series model supports encoding text and pictures at the same time, while the traditional clip model can only support one format for encoding at a time. @wirthual
现阶段 UV 更加现代化，几乎现在最火的开源项目用的都是 UV
Great job, please merge this PR as soon as possible
A800 四卡 ---原始邮件--- 发件人: ***@***.***> 发送时间: 2024年1月6日(周六) 下午3:36 收件人: ***@***.***>; 抄送: ***@***.******@***.***>; 主题: Re: [allwefantasy/byzer-llm] 按照文档运行 bge 模型不正常 (Issue #13) 代码 import ray from byzerllm.utils.client import ByzerLLM,LLMRequest,InferBackend ray.init(address="auto",namespace="default",ignore_reinit_error=True) llm =...