0
代码
代码
Issues
Pull Requests
讨论
Wiki
分析
0
ascend-robotascend-robot【bugfix】自动调优计算yaml配置md5问题修复
d250e694创建于 14 天前历史提交
文件最后提交记录最后更新时间
conftest.py
【msmodelslim】刷新文件头部声明和版权 Co-authored-by: caishengcheng<caishengcheng@huawei.com> # message auto-generated for no-merge-commit merge: !28 merge license into master 【msmodelslim】刷新文件头部声明和版权 Created-by: caishengcheng Commit-by: caishengcheng Merged-by: ascend-robot Description: 【msmodelslim】刷新文件头部声明和版权 See merge request: Ascend/msmodelslim!284 个月前
test_base_dataset_loader.py
Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Co-authored-by: xiaoheng181<eudemoniaxh@163.com> # message auto-generated for no-merge-commit merge: !139 merge qwen2_5_omni_pr4 into master Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Created-by: xiaoheng181 Commit-by: xiaoheng181 Merged-by: ascend-robot Description: 增加jsonl datasetloader和indexed_directory datasetloader单元测试 test/cases/infra/test_base_dataset_loader.py test/cases/infra/test_jsonl_dataset_loader.py test/cases/infra/test_indexed_directory_dataset_loader.py See merge request: Ascend/msmodelslim!1393 个月前
test_indexed_directory_dataset_loader.py
Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Co-authored-by: xiaoheng181<eudemoniaxh@163.com> # message auto-generated for no-merge-commit merge: !139 merge qwen2_5_omni_pr4 into master Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Created-by: xiaoheng181 Commit-by: xiaoheng181 Merged-by: ascend-robot Description: 增加jsonl datasetloader和indexed_directory datasetloader单元测试 test/cases/infra/test_base_dataset_loader.py test/cases/infra/test_jsonl_dataset_loader.py test/cases/infra/test_indexed_directory_dataset_loader.py See merge request: Ascend/msmodelslim!1393 个月前
test_jsonl_dataset_loader.py
Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Co-authored-by: xiaoheng181<eudemoniaxh@163.com> # message auto-generated for no-merge-commit merge: !139 merge qwen2_5_omni_pr4 into master Qwen2.5 Omni模型W8A8量化适配【part4】增加jsonl datasetloader和indexed_directory datasetloader单元测试 Created-by: xiaoheng181 Commit-by: xiaoheng181 Merged-by: ascend-robot Description: 增加jsonl datasetloader和indexed_directory datasetloader单元测试 test/cases/infra/test_base_dataset_loader.py test/cases/infra/test_jsonl_dataset_loader.py test/cases/infra/test_indexed_directory_dataset_loader.py See merge request: Ascend/msmodelslim!1393 个月前
test_legacy_directory_dataset_loader.py
Qwen2.5 Omni模型W8A8量化适配【part5】更新config.ini和lab_practice，增加legacy datasetloader单元测试 Co-authored-by: xiaoheng181<eudemoniaxh@163.com> # message auto-generated for no-merge-commit merge: !140 merge qwen2_5_omni_pr5 into master Qwen2.5 Omni模型W8A8量化适配【part5】更新config.ini和lab_practice，增加legacy datasetloader单元测试 Created-by: xiaoheng181 Commit-by: xiaoheng181 Merged-by: ascend-robot Description: 更新config.ini和lab_practice，增加legacy datasetloader单元测试 config/config.ini lab_practice/qwen2_5_omni_thinker/qwen2_5_omni_thinker_w8a8.yaml test/cases/infra/test_legacy_directory_dataset_loader.py See merge request: Ascend/msmodelslim!1403 个月前
test_prechecker.py
【bugfix】精度从float改为decimal，以符合直觉 Co-authored-by: joejoezhou<zhourongchen1@huawei.com> # message auto-generated for no-merge-commit merge: !243 merge bugfix/accuracy_type into master 【bugfix】精度从float改为decimal，以符合直觉 Created-by: joejoezhou Commit-by: joejoezhou Merged-by: ascend-robot Description: 1、调优策略协议定义中精度相关参数从float改为decimal，如accuracy、target、tolerance 2、数据类序列化时指定json形式，防止decimal序列化失败 3、默认精度从float 0.0改为deciaml '0' 4、单测增加边界用例，accuracy 0.94 target 0.95 tolerance 0.01应通过精度验收 See merge request: Ascend/msmodelslim!2432 个月前
test_service_oriented_evaluate_service.py
【bugfix】精度从float改为decimal，以符合直觉 Co-authored-by: joejoezhou<zhourongchen1@huawei.com> # message auto-generated for no-merge-commit merge: !243 merge bugfix/accuracy_type into master 【bugfix】精度从float改为decimal，以符合直觉 Created-by: joejoezhou Commit-by: joejoezhou Merged-by: ascend-robot Description: 1、调优策略协议定义中精度相关参数从float改为decimal，如accuracy、target、tolerance 2、数据类序列化时指定json形式，防止decimal序列化失败 3、默认精度从float 0.0改为deciaml '0' 4、单测增加边界用例，accuracy 0.94 target 0.95 tolerance 0.01应通过精度验收 See merge request: Ascend/msmodelslim!2432 个月前
test_vlm_dataset_loader.py
Qwen2.5 Omni模型W8A8量化适配【part3】重构多模态模型数据加载器 Co-authored-by: xiaoheng181<eudemoniaxh@163.com> # message auto-generated for no-merge-commit merge: !134 merge qwen2_5_omni_pr3 into master Qwen2.5 Omni模型W8A8量化适配【part3】重构多模态模型数据加载器 Created-by: xiaoheng181 Commit-by: xiaoheng181 Merged-by: ascend-robot Description: 重构多模态模型数据加载器 msmodelslim/cli/auto_tuning/\_\_main\_\_.py msmodelslim/cli/naive_quantization/\_\_main\_\_.py msmodelslim/infra/dataset_loader/\_\_init\_\_.py msmodelslim/infra/dataset_loader/base_dataset_loader.py msmodelslim/infra/dataset_loader/indexed_directory_dataset_loader.py msmodelslim/infra/dataset_loader/jsonl_dataset_loader.py msmodelslim/infra/dataset_loader/legacy_directory_dataset_loader.py msmodelslim/infra/dataset_loader/vlm_dataset_loader.py msmodelslim/model/qwen2_5_vl/model_adapter.py msmodelslim/model/qwen3_vl/model_adapter.py msmodelslim/model/qwen3_vl_moe/model_adapter.py test/cases/infra/test_vlm_dataset_loader.py See merge request: Ascend/msmodelslim!1343 个月前
test_yaml_practice_accuracy_manager.py
【bugfix】自动调优计算yaml配置md5问题修复 Co-authored-by: xyxin_006<xyxin_hit@163.com> # message auto-generated for no-merge-commit merge: !420 merge bugfix/auto_tune into master 【bugfix】自动调优计算yaml配置md5问题修复 Created-by: xyxin_006 Commit-by: xyxin_006 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?) 问题：自动调优精度复用机制是基于yaml配置的md5值，当前的md5值计算会考虑yaml的 metadata，其中config_id会随着迭代次数而变化，从而导致一样的量化配置计算出的md5值不一致，无法复用历史精度数据。 修复后：自动调优中计算practice的md5值不考虑 metadata ## 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!42014 天前
test_yaml_practice_history_manager.py
【bugfix】自动调优计算yaml配置md5问题修复 Co-authored-by: xyxin_006<xyxin_hit@163.com> # message auto-generated for no-merge-commit merge: !420 merge bugfix/auto_tune into master 【bugfix】自动调优计算yaml配置md5问题修复 Created-by: xyxin_006 Commit-by: xyxin_006 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?) 问题：自动调优精度复用机制是基于yaml配置的md5值，当前的md5值计算会考虑yaml的 metadata，其中config_id会随着迭代次数而变化，从而导致一样的量化配置计算出的md5值不一致，无法复用历史精度数据。 修复后：自动调优中计算practice的md5值不考虑 metadata ## 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!42014 天前