0
代码
代码
Issues
Pull Requests
讨论
Wiki
分析
0
ascend-robotascend-robot【feature】 支持FA3的混合量化配置及保存
dfbca739创建于 4 小时前历史提交
文件最后提交记录最后更新时间
api
Optimized MXFP4 quantization Co-authored-by: hwyang<huiwen.yang@huawei.com> # message auto-generated for no-merge-commit merge: !239 merge optimized_mxfp4 into master Optimized MXFP4 quantization Created-by: hwyang Commit-by: hwyang Merged-by: ascend-robot Description: Optimized MXFP4 quantization Fixes [#124](https://gitcode.com/Ascend/msmodelslim/issues/124) See merge request: Ascend/msmodelslim!2392 个月前
test_activation_dynamic.py
【UT】新增fa3动态量化、在线旋转ut Co-authored-by: libarry<870390541@qq.com> # message auto-generated for no-merge-commit merge: !57 merge fa3_rot_ut into master 【UT】新增fa3动态量化、在线旋转ut Created-by: libarry Commit-by: libarry Merged-by: ascend-robot Description: add fa3 and online quarot ut See merge request: Ascend/msmodelslim!574 个月前
test_activation_static.py
【feature】 支持FA3的混合量化配置及保存 Co-authored-by: wangsihao<wangsihao5@h-partners.com> # message auto-generated for no-merge-commit merge: !483 merge master into master 【feature】 支持FA3的混合量化配置及保存 Created-by: wangsihao Commit-by: wangsihao 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)。 ## PR描述 (What this PR does / why we need it?) 支持FA3量化中的不同策略和粒度的混合配置 如：fa_q 动态量化，fa_k/fa_v 静态量化 量化粒度支持FP8/INT8，其中INT8仅支持静态量化 ## 功能验证 (How was this patch tested?) - [_] 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 See merge request: Ascend/msmodelslim!4834 小时前
test_flatquant.py
【UT】补充FlatQuant算法UT测试用例 Co-authored-by: gcw_w7eh8umq<yueziyang1@huawei.com> # message auto-generated for no-merge-commit merge: !325 merge master into master 【UT】补充FlatQuant算法UT测试用例 Created-by: gcw_w7eh8umq Commit-by: gcw_w7eh8umq 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!3251 个月前
test_fp8_activation_static.py
【feature】 支持FA3的混合量化配置及保存 Co-authored-by: wangsihao<wangsihao5@h-partners.com> # message auto-generated for no-merge-commit merge: !483 merge master into master 【feature】 支持FA3的混合量化配置及保存 Created-by: wangsihao Commit-by: wangsihao 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)。 ## PR描述 (What this PR does / why we need it?) 支持FA3量化中的不同策略和粒度的混合配置 如：fa_q 动态量化，fa_k/fa_v 静态量化 量化粒度支持FP8/INT8，其中INT8仅支持静态量化 ## 功能验证 (How was this patch tested?) - [_] 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 See merge request: Ascend/msmodelslim!4834 小时前
test_int8_activation_static.py
【feature】 支持FA3的混合量化配置及保存 Co-authored-by: wangsihao<wangsihao5@h-partners.com> # message auto-generated for no-merge-commit merge: !483 merge master into master 【feature】 支持FA3的混合量化配置及保存 Created-by: wangsihao Commit-by: wangsihao 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)。 ## PR描述 (What this PR does / why we need it?) 支持FA3量化中的不同策略和粒度的混合配置 如：fa_q 动态量化，fa_k/fa_v 静态量化 量化粒度支持FP8/INT8，其中INT8仅支持静态量化 ## 功能验证 (How was this patch tested?) - [_] 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 See merge request: Ascend/msmodelslim!4834 小时前
test_non_fusion_smooth_quant_ir.py
增加开发者测试指南 Co-authored-by: 李明宇<limingyu35@h-partners.com> # message auto-generated for no-merge-commit merge: !416 merge master-utdocs into master 【feature】【DOCS】增加开发者测试指南 Created-by: code_mingming Commit-by: code_mingming;李明宇 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?) 1.提交测试用例规范指南，用户可按资料执行UT用例测试。 2.修改run_ut.sh 可以参数控制只进行modelslim_vl的相关用例测试。 3.修复部分ut，增加之前未开启的ir目录。 ## 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!41614 天前
test_quarot.py
【ut】: add UT for QuaRotExtraInfo IR (PR #141) Co-authored-by: rookie_hongchuan<hongchuan6@h-partners.com> # message auto-generated for no-merge-commit merge: !219 merge test/pr-141-quarot-extra-info-ut into master 【ut】: add UT for QuaRotExtraInfo IR (PR #141) Created-by: rookie_hongchuan Commit-by: rookie_hongchuan Merged-by: ascend-robot Description: ## 说明 为 PR #141（支持导出 QuaRot 所使用的全局旋转矩阵）引入的 IR 补充单元测试。 ## 改动 - **test/cases/ir/test_quarot.py** - QuarotOfflineRotationInfo：初始化后 global_rotation 与传入一致 - QuaRotExtraInfoHookIR：初始化持有 rotation_info、__call__ 不改变参数、wrapper_module 返回 QuaRotExtraInfoWrapperIR 并移除 hook - QuaRotExtraInfoWrapperIR：初始化持有 wrapped_module/rotation_info、is_atomic() 为 False、forward 透传至 wrapped_module ## 用例命名 遵循「对象-条件-断言」规范：test_<对象>_<条件>_<断言>。 ## 关联 - 补充 PR #141 的 UT 覆盖 See merge request: Ascend/msmodelslim!2192 个月前