ikun-404

Thank you for your reply in your busy schedule. When the host is not doing anything, can the VM be adjusted to no more than 50% or fixed at 50%?...

> > Thank you for your reply in your busy schedule. When the host is not doing anything, can the VM be adjusted to no more than 50% or fixed...

> > > > Thank you for your reply in your busy schedule. When the host is not doing anything, can the VM be adjusted to no more than 50%...

I have the same problem

same issue

> > So far, have you checked the Lora button in WebUI to see if your Lora is showing up there? After some investigation, it seems that all the .safetensors...

有是有加载到GPU，GPU显存利用的很少，对比了一下，cpu和gpu效率一样，也是神奇，感觉是没调好 video_scene_seg = pipeline(Tasks.movie_scene_segmentation, model='damo/cv_resnet50-bert_video-scene-segmentation_movienet', device='gpu')

> 镜像registry.cn-beijing.aliyuncs.com/modelscope-repo/modelscope:ubuntu22.04-cuda11.8.0-py310-torch2.1.0-tf2.14.0-1.10.0，推理时长在40s左右，显存占用11.5G。你这里可能是文件下载占用了大部分时间。 感谢你的回复，看样子并不像在下载文件占用的时间，执行下一个视频也需要这么长时间，这边是自己构建的环境，后续使用官方镜像试下