[Refactor] Adapt v0.8.3 for MindONE models · Pull Request !503 · MindSpore/vllm-mindspore

1. adapt v0.8.3
---
<!--  Thanks for sending a pull request!  Here are some tips for you:

1) If this is your first time, please read our contributor guidelines: https://gitee.com/mindspore/mindspore/blob/master/CONTRIBUTING.md

2) If you want to contribute your code but don't know who will review and merge, please add label `mindspore-assistant` to the pull request, we will find and do it as soon as possible.
-->

**What type of PR is this?**

/kind refactor

**What does this PR do / why do we need it**:

**Which issue(s) this PR fixes**:

Fixes #ICELSI

**Code review checklist [【代码检视checklist说明】](https://gitee.com/mindspore/community/blob/master/security/code_review_checklist_mechanism.md)**:

+ - [ ] 是否进行返回值校验 (禁止使用void屏蔽安全函数、自研函数返回值，C++标准库函数确认无问题可以屏蔽)
+ - [ ] 是否遵守 ***SOLID原则 / 迪米特法则***
+ - [ ] 是否具备UT测试用例看护 && 测试用例为有效用例 (若新特性无测试用例看护请说明原因)
+ - [ ] 是否为对外接口变更
+ - [ ] 是否涉及官网文档修改

精度报告：
Qwen3:

Prompt: 'MindSpore is', Generated text: ' a deep learning framework that is designed to be highly portable and flexible, making it suitable for a wide range of applications, from simple image classification tasks to complex neural network architectures. One of the key features of MindSpore is its ability to handle various types of data, including tensors, which are fundamental building blocks in deep learning. In this unit, we will delve into the concept of tensor types in MindSpore, particularly focusing on the `TensorType` class and its methods. We will explore how these types are used, their significance, and how they can be applied in practical scenarios.\n\n### Understanding Tensor Types in MindSpore\n\nIn MindSpore, a tensor is a multi-dimensional array of numerical values. Tensors can be used to represent various types of data, such as images, vectors, and matrices. Each tensor has a specific type, which determines the data it can hold and the operations it can perform. The `TensorType` class in MindSpore is a powerful tool for managing these types, providing a way to define and manipulate tensor types at runtime.\n\n#### The `TensorType` Class\n\nThe `TensorType` class in MindSpore is a subclass of `Type` and is used to represent different types of tensors. It encapsulates the'
 
 
Qwen2:

Prompt: 'MindSpore is', Generated text: ' a new generation of deep learning framework, which is based on the PyTorch framework. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of deep learning models. It is a complete deep learning framework, which can be used to build a wide range of'
 
Qwen2.5_vl:
 
Generated text: 'The image shows a group of cheetahs wading through a shallow, muddy water body. The water appears to be turbulent, with waves and splashes around the cheetahs. The cheetahs are partially submerged, with their heads and upper bodies visible above the water. The scene captures the cheetahs in a natural, wild environment, likely in a savanna or grassland habitat.'

类型	指派人员	状态
审查	TronZhang	已完成 (0/0人)
测试	TronZhang	已完成 (0/0人)

MindSpore/vllm-mindspore .gitee-modal { width: 500px !important; }

搜索帮助

MindSpore/vllm-mindspore