search

OpenBMB / MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Apache License 2.0
12.36k stars 867 forks source link

[llamacpp] - Is it possible to provide the ability to perform video inference by the server mode？ #485

Open HaishengLiang opened 2 months ago

HaishengLiang commented 2 months ago

起始日期 | Start Date

No response

实现PR | Implementation PR

No response

相关Issues | Reference Issues

No response

摘要 | Summary

need llama.cpp support video by server mode

基本示例 | Basic Example

none

缺陷 | Drawbacks

none

未解决问题 | Unresolved questions

No response

tc-mb commented 1 week ago

First of all, I'm sorry that I was busy with other projects before and I responded a little late.

Because we have to discuss with llama.cpp officials how to merge the video frame extraction function, this piece is still in the state of consolidation. I will submit a pr that supports sever as soon as possible after the frame extraction code is merged.