文件最后提交记录最后更新时间
【docs】:大模型检查低错修改 Co-authored-by: zzm30<zhengzhimin1@h-partners.com> # message auto-generated for no-merge-commit merge: !333 merge master into master 【docs】:大模型检查低错修改 Created-by: zzm30 Commit-by: zzm30 Merged-by: ascend-robot Description: 感谢您贡献的Pull Request! 在提交之前,请务必阅读 [CONTRIBUTING.md](https://gitcode.com/Ascend/msmodelslim/blob/master/CONTRIBUTING.md)。 Thanks for sending a pull request! BEFORE SUBMITTING, PLEASE READ [CONTRIBUTING.md](https://gitcode.com/Ascend/msmodelslim/blob/master/CONTRIBUTING.md). ## PR描述 (What this PR does / why we need it?) - 请明确说明您提交PR的变更内容。本部分旨在概述所做的变更,以及此PR是如何解决该问题的。请尽可能地提供有助于评审人员更高效、更快速完成检视审查的实用说明。 - 请说明为何需要这些更改,例如具体的使用场景或bug描述。 - 关联issue号(如果有)。 - Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue. If possible, please consider writing useful notes for better and faster reviews in your PR. - Please clarify why the changes are needed. For instance, the use case and bug description. - Related issue number (if any) ## 面向用户的变更 (Does this PR introduce _any_ user-facing change)? - 请注意,这里指的是**任何**面向用户的变更,包括但不限于API、用户界面或其他使用方式上的变更。 - Note that it means *any* user-facing change including all aspects such as API, interface or other behavior changes. ## 功能验证 (How was this patch tested?) 请确认CI已通过增量及存量的单元测试用例。 如果本次测试方式与常规单元测试不同,请详细说明您的测试步骤(最好提供完整的可复现的操作路径及关键截图),以便Committer能够快速复现验证,也便于后续的维护。 如果未添加测试,请说明未添加的原因,以及为何难添加测试。 - [_] 功能自验 - [_] 本地自验截图(涉及个人标识符等敏感信息请注意脱敏) - [_] 新增/变更内容是否已新增/适配UT测试用例看护 CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. - [_] Self-verification of the feature. - [_] Screenshot of local self-verification (please anonymize any sensitive information such as personal identifiers) - [_] Have new or modified unit test (UT) cases been added or adapted to cover the newly added or changed content? See merge request: Ascend/msmodelslim!3331 个月前
README.md

Qwen3-Next 量化说明

模型介绍

  • Qwen3-Next-80B-A3B-Instruct 代表了Qwen团队推出的下一代基础模型,专为极端上下文长度和大规模参数效率进行了优化。其引入了一系列架构创新,在最大化性能的同时最小化计算成本。

使用前准备

昇腾AI处理器支持情况

  • 支持Atlas A2训练、推理产品,Atlas A3训练、推理产品

支持的模型版本与量化策略

模型系列 模型版本 HuggingFace链接 W8A8 W8A16 W4A8 W4A16 W4A4 稀疏量化 KV Cache Attention 量化命令
Qwen3-Next Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct W8A8

说明:

  • ✅ 表示该量化策略已通过msModelSlim官方验证,功能完整、性能稳定,建议优先采用。
  • 空格表示该量化策略暂未通过msModelSlim官方验证,用户可根据实际需求进行配置尝试,但量化效果和功能稳定性无法得到官方保证。
  • 点击量化命令列中的链接可跳转到对应的具体量化命令

量化权重生成

使用示例

  • 请将${MODEL_PATH}替换为用户实际浮点权重路径,${SAVE_PATH}替换为量化权重保存路径。

Qwen3-Next-80B-A3B-Instruct

Qwen3-Next-80B-A3B-Instruct W8A8量化

该模型的量化已经集成至一键量化

msmodelslim quant --model_path ${MODEL_PATH} --save_path ${SAVE_PATH} --device npu --model_type Qwen3-Next-80B-A3B-Instruct --quant_type w8a8 --trust_remote_code True