Incccc

下载打包好插件的版本初始化报错

4

 如图，安装带了插件的版本以后初始化报错 另外想请问下，怎么解决gitgub下载插件的时候超时，无响应的问题，貌似我用代理的镜像地址也不行，试了好几个博主的配置都有类似问题

how to pack fastertransformer

1

Hi, does FT now support pack the project into a standard python package like whl format, just like huggiface transformers? so that it would be much more convenient to import...

incompatible number of blobs for layer bn0

2

hi,I am trying to convert a model trained by mxnet into caffemodel,however after i get the caffemodel file,and tring to test the model on caffe framework,the error occurs:check failed:target_blobs.size() ==...

[Feature] InternVL-Chat-V1.5 Support

7

### Motivation does lmdeploy support the InternVL-Chat-V1.5 VL model now? Is it supoorted on the main branch?Thx ### Related resources _No response_ ### Additional context _No response_

是否有计划优化GPU上的推理加速

3

目前社区LLM采用主流GPTQ量化之后，量化层的kernel实现基本是负向优化，是否有计划支持GPU上量化后的模型推理加速。

Hi, thx for your inspiring work, I try to reproduce the work following the Example in the readme, however it seems to raise an error about network connecting, I wonder...

scenevlm finetune

8

significant work！ How can user SFT the scenevlm model under the own specified scene?