Matthew Guan

icon indicating an email [email protected]

icon location chengdu icon location The more hard,the more lucky~

Results 18 comments of Matthew Guan

I can't find file `CJK.enc'

已解决！ 请下载完整版的mactex（mac'系统）

[Bug]TypeError: class `MMArchitectureQuant` in mmrazor/models/algorithms/quantization/mm_architecture.py: _fuse_fx() got an unexpected keyword argument 'graph_module'

> I apologize for the inconvenience, but I was unable to reproduce the issue. > > If the #554 is unresolved, it should not reach the `_fuse_fx` step. Perhaps you...

部署yi-vl模型报错cannot import name 'VllmGenerationConfig' from 'swift.llm.utils' (/home/ubuntu/project/swift/swift/llm/utils/__init__.py)

> 已经支持多模态部署：https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/MLLM%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3.md @Jintao-Huang 请问swift是否已经支持多模态 vllm openai 后端？

error: ‘Fill’ was not declared in this scope

我也遇到了相同问题，请问你解决了吗？ I have the same problem, please ask you to solve it?

error: ‘Fill’ was not declared in this scope

请问你知道在哪里可以找到可以在cityscapes上训练的mrcnn仓库吗？最好是tensorflow版本的，谢谢~ Do you know where can find MRCNN code training on CitysCapes dataset in github? Preferably the tensorflow version. Thank you！

Best Practices for Inference and Fine-Tuning with MiniCPM-V 2.6

请教一下，可以提供一下 Async+VLLM 推理 minicpmv2-6的代码么。

Best Practices for Inference and Fine-Tuning with MiniCPM-V 2.6

> > 请教一下，可以提供一下 Async+VLLM 推理 minicpmv2-6的代码么。 > > swift deploy 走的是 Async+VLLM的 > > 客户端调用方式可以查看这里的文档： > > https://swift.readthedocs.io/zh-cn/latest/Multi-Modal/vLLM%E6%8E%A8%E7%90%86%E5%8A%A0%E9%80%9F%E6%96%87%E6%A1%A3.html#id4 这个文档显示的是 openai的客户端调用方法，openai 是同步调用吧？ 异步调用代码是不是得用 asyncio 包吧？

Best Practices for Inference and Fine-Tuning with MiniCPM-V 2.6

> 服务端: > > ```shell > CUDA_VISIBLE_DEVICES=0 swift deploy --model_type minicpm-v-v2_6-chat --infer_backend vllm --max_model_len 8192 > ``` > > 客户端： > > ```python > import asyncio > from swift.llm import...

Best Practices for Inference and Fine-Tuning with MiniCPM-V 2.6

> 1. 如何使用 python sdk启动服务 > > ```python > import os > os.environ['CUDA_VISIBLE_DEVICES'] = '0' > from swift.llm import deploy_main, DeployArguments > > # 与swift deploy相同的参数 > deploy_main(DeployArguments(...)) > ```...

Best Practices for Inference and Fine-Tuning with MiniCPM-V 2.6

> > 1. 如何使用 python sdk启动服务 > > > > ```python > > import os > > os.environ['CUDA_VISIBLE_DEVICES'] = '0' > > from swift.llm import deploy_main, DeployArguments > > >...