Willian7004

如何在运行app.py时加载已下载的模型

2

我已经下载 release中的模型放到与app.py相同的目录，但运行时报错requests.exceptions.SSLError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /jameslahm/yolov10m/resolve/main/config.json (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1133)')))"), '(Request ID: 67f7aade-cb86-49fb-8825-34aa59aa96db)')，说明没有成功加载本地模型，后面尝试把模型放到weights文件夹和项目中的models文件夹均不能加载。为了方便使用，请在readme中添加加载本地模型的方法。

Will you support multi-GPU tensor parallelism in the future?

4

I run this model on cloud server so I can choose to rent multi-GPU,it takes more than 1 hour to generate a video in 1 GPU and it doesn't get...

support nvidia/Cosmos-1.0-Prompt-Upsampler-12B-Text2World

2

It is said that this model is based on Mistral Nemo, but I got unknown architecture error when I import the model. 

use device map instead of quantalization to save VRAM and keep image quality

2

I tried [Inference with 8bit](https://github.com/NVlabs/Sana/blob/main/asset/docs/8bit_sana.md) with SANA1.5 1.6B and the image quality is worse than the demo. Then I tried device_map, the inference on 8g VRAM is about 65% slower...

0.4.4版本omni模型音频输入和音频输出无法正常运行

11

设备：骁龙8gen1，安卓15，8g内存 图片输入正常，而音频输入在较短的perfill后闪退了，应该不是内存问题。 选择音频输出时，没有实时输出，生成结束也没有显示生成的音频 

是否计划推出Windows和Linux版本的MNN Chat

1

目前MNN Chat只有安卓版本，在Windows和Linux上目前没有比较好的Omni模型推理框架，能否推出Windows和Linux版本的MNN Chat以便部署Omni模型？

### 公众号名称 bb姬 ### 领域 ACG ### 介绍 动漫和游戏评论 ### 文章地址 https://mp.weixin.qq.com/s?__biz=MzU3Nzc1MzMzOA==&mid=2247797825&idx=1&sn=64e4108caadffaf6b234c4c4a5e9114a

Feature Request: Support GLM-4.1V-9B-Thinking

12

### Prerequisites - [x] I am running the latest code. Mention the version if possible as well. - [x] I carefully followed the [README.md](https://github.com/ggml-org/llama.cpp/blob/master/README.md). - [x] I searched using keywords...