| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
docs: 【直播作业】填写 YOLOv13 最优多流配置(#516) Co-authored-by: Wjieee<1731907853@qq.com> # message auto-generated for no-merge-commit merge: !4429 merge develop into develop docs: 【直播作业】填写 YOLOv13 最优多流配置(#516) Created-by: Wjieee Commit-by: Wjieee Merged-by: cann-robot Description: ## 基本信息 - **所选 Example**：YOLOv13 - **CANNLab 环境**：Ubuntu 20.04 + aarch64 - **CANN 版本**：社区版 9.2.0 (Weekly) - **芯片规格**：Ascend910 (NPU Name: 9362)，soc_version=Ascend910_9362 - **关联 Issue**：[#516]https://gitcode.com/cann/ge/issues/516 ## 测试命令 ### ATC 编译命令（以最优配置为例） bash atc --model=yolov13n.onnx \ --framework=5 \ --output=./model/yolov13_LoadBalance_55 \ --soc_version=Ascend910_9362 \ --input_shape="images:1,3,640,640" \ --output_type=FP32 \ --multi_stream_parallel_mode=LoadBalance:55 ### 推理测试命令 bash ./out/yolov13_main \ --model=./model/yolov13_LoadBalance_55.om \ --input=./data/bus.bin \ --warmup-runs=10 \ --runs=90 ## 固定参数 - ONNX 模型：yolov13n.onnx（input_shape="images:1,3,640,640"） - 输入数据：bus.bin - soc_version：Ascend910_9362 - --warmup-runs=10 - --runs=90 - --multi_stream_parallel_mode 为唯一寻优变量 ## 测试结果 | 配置角色 | 多流配置 | 主评价指标平均耗时（ms） | 正式统计任务数 | |:---|:---|:---|:---| | Base 配置 | 未配置多流参数 | 2.631 | 90 | | 候选配置 | cv | 2.568 | 90 | | 候选配置 | LoadBalance:1 | 2.797 | 90 | | 候选配置 | LoadBalance:2 | 2.613 | 90 | | 候选配置 | LoadBalance:3 | 2.386 | 90 | | 候选配置 | LoadBalance:4 | 2.472 | 90 | | 候选配置 | LoadBalance:5 | 2.281 | 90 | | 候选配置 | LoadBalance:6 | 2.291 | 90 | | 候选配置 | LoadBalance:7 | 2.334 | 90 | | 候选配置 | LoadBalance:8 | 2.270 | 90 | | 候选配置 | LoadBalance:9 | 2.422 | 90 | | 候选配置 | LoadBalance:10 | 2.308 | 90 | | 候选配置 | LoadBalance:11 | 2.421 | 90 | | 候选配置 | LoadBalance:12 | 2.450 | 90 | | 候选配置 | LoadBalance:13 | 2.462 | 90 | | 候选配置 | LoadBalance:14 | 2.277 | 90 | | 候选配置 | LoadBalance:15 | 2.363 | 90 | | 候选配置 | LoadBalance:16 | 2.412 | 90 | | 候选配置 | LoadBalance:17 | 2.281 | 90 | | 候选配置 | LoadBalance:18 | 2.302 | 90 | | 候选配置 | LoadBalance:19 | 2.289 | 90 | | 候选配置 | LoadBalance:20 | 2.428 | 90 | | 候选配置 | LoadBalance:21 | 2.283 | 90 | | 候选配置 | LoadBalance:22 | 2.489 | 90 | | 候选配置 | LoadBalance:23 | 2.285 | 90 | | 候选配置 | LoadBalance:24 | 2.269 | 90 | | 候选配置 | LoadBalance:25 | 2.305 | 90 | | 候选配置 | LoadBalance:26 | 2.277 | 90 | | 候选配置 | LoadBalance:27 | 2.325 | 90 | | 候选配置 | LoadBalance:28 | 2.442 | 90 | | 候选配置 | LoadBalance:29 | 2.416 | 90 | | 候选配置 | LoadBalance:30 | 2.263 | 90 | | 候选配置 | LoadBalance:31 | 2.290 | 90 | | 候选配置 | LoadBalance:32 | 2.423 | 90 | | 候选配置 | LoadBalance:33 | 2.438 | 90 | | 候选配置 | LoadBalance:34 | 2.423 | 90 | | 候选配置 | LoadBalance:35 | 2.419 | 90 | | 候选配置 | LoadBalance:36 | 2.418 | 90 | | 候选配置 | LoadBalance:37 | 2.277 | 90 | | 候选配置 | LoadBalance:38 | 2.270 | 90 | | 候选配置 | LoadBalance:39 | 2.271 | 90 | | 候选配置 | LoadBalance:40 | 2.289 | 90 | | 候选配置 | LoadBalance:41 | 2.271 | 90 | | 候选配置 | LoadBalance:42 | 2.289 | 90 | | 候选配置 | LoadBalance:43 | 2.441 | 90 | | 候选配置 | LoadBalance:44 | 2.414 | 90 | | 候选配置 | LoadBalance:45 | 2.424 | 90 | | 候选配置 | LoadBalance:46 | 2.269 | 90 | | 候选配置 | LoadBalance:47 | 2.274 | 90 | | 候选配置 | LoadBalance:48 | 2.272 | 90 | | 候选配置 | LoadBalance:49 | 2.301 | 90 | | 候选配置 | LoadBalance:50 | 2.275 | 90 | | 候选配置 | LoadBalance:51 | 2.270 | 90 | | 候选配置 | LoadBalance:52 | 2.438 | 90 | | 候选配置 | LoadBalance:53 | 2.413 | 90 | | 候选配置 | LoadBalance:54 | 2.429 | 90 | | **最优配置** | **LoadBalance:55** | **2.261** | **90** | | 候选配置 | LoadBalance:56 | 2.267 | 90 | | 候选配置 | LoadBalance:57 | 2.295 | 90 | | 候选配置 | LoadBalance:58 | 2.287 | 90 | | 候选配置 | LoadBalance:59 | 2.279 | 90 | | 候选配置 | LoadBalance:60 | 2.277 | 90 | | 候选配置 | LoadBalance:61 | 2.445 | 90 | | 候选配置 | LoadBalance:62 | 2.421 | 90 | | 候选配置 | LoadBalance:63 | 2.428 | 90 | | 候选配置 | LoadBalance:64 | 2.272 | 90 | | 候选配置 | MainStream:1 | 2.644 | 90 | | 候选配置 | MainStream:2 | 2.741 | 90 | | 候选配置 | MainStream:3 | 2.662 | 90 | | 候选配置 | MainStream:4 | 2.489 | 90 | | 候选配置 | MainStream:5 | 2.651 | 90 | | 候选配置 | MainStream:6 | 2.613 | 90 | | 候选配置 | MainStream:7 | 2.622 | 90 | | 候选配置 | MainStream:8 | 2.618 | 90 | | 候选配置 | MainStream:9 | 2.453 | 90 | | 候选配置 | MainStream:10 | 2.472 | 90 | | 候选配置 | MainStream:11 | 2.628 | 90 | | 候选配置 | MainStream:12 | 2.625 | 90 | | 候选配置 | MainStream:13 | 2.491 | 90 | | 候选配置 | MainStream:14 | 2.631 | 90 | | 候选配置 | MainStream:15 | 2.466 | 90 | | 候选配置 | MainStream:16 | 2.480 | 90 | | 候选配置 | MainStream:17 | 2.471 | 90 | | 候选配置 | MainStream:18 | 2.483 | 90 | | 候选配置 | MainStream:19 | 2.469 | 90 | | 候选配置 | MainStream:20 | 2.480 | 90 | | 候选配置 | MainStream:21 | 2.505 | 90 | | 候选配置 | MainStream:22 | 2.644 | 90 | | 候选配置 | MainStream:23 | 2.488 | 90 | | 候选配置 | MainStream:24 | 2.643 | 90 | | 候选配置 | MainStream:25 | 2.617 | 90 | | 候选配置 | MainStream:26 | 2.618 | 90 | | 候选配置 | MainStream:27 | 2.612 | 90 | | 候选配置 | MainStream:28 | 2.461 | 90 | | 候选配置 | MainStream:29 | 2.464 | 90 | | 候选配置 | MainStream:30 | 2.623 | 90 | | 候选配置 | MainStream:31 | 2.618 | 90 | | 候选配置 | MainStream:32 | 2.488 | 90 | | 候选配置 | MainStream:33 | 2.625 | 90 | | 候选配置 | MainStream:34 | 2.468 | 90 | | 候选配置 | MainStream:35 | 2.473 | 90 | | 候选配置 | MainStream:36 | 2.475 | 90 | | 候选配置 | MainStream:37 | 2.478 | 90 | | 候选配置 | MainStream:38 | 2.474 | 90 | | 候选配置 | MainStream:39 | 2.479 | 90 | | 候选配置 | MainStream:40 | 2.502 | 90 | | 候选配置 | MainStream:41 | 2.644 | 90 | | 候选配置 | MainStream:42 | 2.494 | 90 | | 候选配置 | MainStream:43 | 2.650 | 90 | | 候选配置 | MainStream:44 | 2.615 | 90 | | 候选配置 | MainStream:45 | 2.623 | 90 | | 候选配置 | MainStream:46 | 2.619 | 90 | | 候选配置 | MainStream:47 | 2.454 | 90 | | 候选配置 | MainStream:48 | 2.471 | 90 | | 候选配置 | MainStream:49 | 2.629 | 90 | | 候选配置 | MainStream:50 | 2.625 | 90 | | 候选配置 | MainStream:51 | 2.493 | 90 | | 候选配置 | MainStream:52 | 2.630 | 90 | | 候选配置 | MainStream:53 | 2.467 | 90 | | 候选配置 | MainStream:54 | 2.480 | 90 | | 候选配置 | MainStream:55 | 2.471 | 90 | | 候选配置 | MainStream:56 | 2.484 | 90 | | 候选配置 | MainStream:57 | 2.470 | 90 | | 候选配置 | MainStream:58 | 2.481 | 90 | | 候选配置 | MainStream:59 | 2.505 | 90 | | 候选配置 | MainStream:60 | 2.638 | 90 | | 候选配置 | MainStream:61 | 2.489 | 90 | | 候选配置 | MainStream:62 | 2.641 | 90 | | 候选配置 | MainStream:63 | 2.618 | 90 | | 候选配置 | MainStream:64 | 2.616 | 90 | ## 最优配置 - **最优配置**：--multi_stream_parallel_mode=LoadBalance:55 - **Base 配置平均耗时**：2.631 ms - **最优配置平均耗时**：2.261 ms - **性能提升**：约 14.1% ## 关键日志 ### Base 配置日志 [INFO] load model /mnt/workspace/projects/ge/examples/acl/5_sample_yolov13/model/yolov13.om success. [INFO] BENCHMARK aclmdlExecute run=0 latency_us=2625 [INFO] BENCHMARK aclmdlExecute run=1 latency_us=2630 [INFO] BENCHMARK aclmdlExecute run=2 latency_us=2633 [INFO] BENCHMARK aclmdlExecute run=3 latency_us=2632 [INFO] BENCHMARK aclmdlExecute run=87 latency_us=2632 [INFO] BENCHMARK aclmdlExecute run=88 latency_us=2628 [INFO] BENCHMARK aclmdlExecute run=89 latency_us=2631 [INFO] Average aclmdlExecute latency: 2.631 ms [INFO] YOLOv13 SAMPLE PASSED. ### 最优配置 LoadBalance:55 日志 [INFO] load model /mnt/workspace/projects/ge/examples/acl/5_sample_yolov13/model/yolov13_LoadBalance_55.om success. [INFO] BENCHMARK aclmdlExecute run=0 latency_us=2269 [INFO] BENCHMARK aclmdlExecute run=1 latency_us=2267 [INFO] BENCHMARK aclmdlExecute run=2 latency_us=2266 [INFO] BENCHMARK aclmdlExecute run=3 latency_us=2258 [INFO] BENCHMARK aclmdlExecute run=87 latency_us=2257 [INFO] BENCHMARK aclmdlExecute run=88 latency_us=2280 [INFO] BENCHMARK aclmdlExecute run=89 latency_us=2285 [INFO] Average aclmdlExecute latency: 2.261 ms [INFO] YOLOv13 SAMPLE PASSED. See merge request: cann/ge!4429 | 29 天前 | |
【PR】:rename user-guides Co-authored-by: sophia1213<sophie.chen@huawei.com> # message auto-generated for no-merge-commit merge: !3814 merge develop into develop 【PR】:rename user-guides Created-by: sophia1213 Commit-by: sophia1213 Merged-by: cann-robot Description: # Pull Request ## 描述 重命名docs目录下的user-guides为user_guides。 ## 变更类型 请选择本次引入的变更类型： <!-- [x] 表示选中 --> - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [x] 📝 文档内容更新 ## 关联的Issue 无 ## 如何测试 根据最新目录进行测试 ## 核对清单 <!-- [x] 表示选中 --> - [ ] 我的代码遵循了项目的代码风格 - [ ] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [ ] 我在标题中使用了合适的类型标签（如： feat:, fix:） - [ ] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 在此添加任何其他关于本次 PR 的说明。 See merge request: cann/ge!3814 | 2 个月前 | |
docs(custom_op): 补齐 tilelang 样例英文 README 与中文版对齐 Co-authored-by: qq_45842700<caodazhou@huawei.com> # message auto-generated for no-merge-commit merge: !4853 merge docs/tilelang-readme-en-sync into develop docs(custom_op): 补齐 tilelang 样例英文 README 与中文版对齐 Created-by: Dazhou_Cao Commit-by: qq_45842700 Merged-by: cann-robot Description: # Pull Request ## 描述 三个 tilelang 样例的英文 README（README_en.md）与中文版（README.md）不一致，英文版缺失大量章节。本 PR 将英文 README 补齐为与中文版逐行对齐的完整翻译，与仓库既有惯例（compilable_add_custom、triton_add_custom 中英 README 行数一致）保持一致。 主要补充内容： - tilelang_add_custom：call 函数签名及说明、CANN 依赖第 2 条、环境变量表、快速运行 4 步说明与预期输出、关键文件说明、算子规格 Output shape 行、分步运行章节 - tilelang_add_custom_online：目录结构注释、call 函数签名及说明、CANN 依赖第 2 条、环境变量表、成功输出示例、关键文件说明、算子规格 Output shape 行、分步运行章节、注意事项补全 2 条；修正交叉链接指向英文版 README_en.md - tilelang_add_custom_offline：目录结构、核心流程（graph_build/ATC/model_exec 三阶段流程图）、TileLang-Ascend 使用范围说明、环境变量表、快速运行 4 步说明与预期输出、算子规格 Output shape 行、序列化格式、关键文件说明、注意事项补全 4 条 同时修正一处中文 README 与代码不一致的描述：offline 样例"关键文件说明"中 Deserialize 原描述为"写临时文件"，与代码实现矛盾（实际链路 Deserialize → LoadSoFromData → WriteVectorToMemfd → memfd_create 从内存加载、不落盘；mkstemps 临时文件仅用于 Compile 阶段），中英文同步修正。 ## 变更类型 请选择本次引入的变更类型： - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [x] 📝 文档内容更新 ## 关联的Issue 无 ## 如何测试 1. 文档类改动，无需运行功能测试 2. 结构校验：三个样例中英 README 的章节标题（h2/h3 数量）、代码围栏数量、总行数逐项对齐（177/208/212 行），且标题与围栏所在行号完全一致 3. 本地 pre-commit 检查全部通过（codespell、end-of-file-fixer、trailing-whitespace、OAT Compliance 等） ## 核对清单 - [x] 我的代码遵循了项目的代码风格 - [x] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [x] 我在标题中使用了合适的类型标签（如：feat:, fix:） - [x] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 - 分支基于 cann/ge develop 创建，仅包含 3 个 README_en.md 补齐与 1 处中英同步修正（offline README.md / README_en.md 各 1 行），不涉及代码改动 See merge request: cann/ge!4853 | 5 天前 | |
docs: dflow python版本要求从3.11更新为3.12 Co-authored-by: lining23666<lining.li@huawei.com> # message auto-generated for no-merge-commit merge: !4686 merge dflow into develop docs: dflow python版本要求从3.11更新为3.12 Created-by: lining23666 Commit-by: lining23666 Merged-by: cann-robot Description: # Pull Request ## 描述 dflow python因使用pybind11，要求编译时和运行时python版本一致。商发版本流水线出包的python版本已从3.11切换为3.12，本次同步更新文档及样例中写死的python 3.11版本为3.12： - docs/zh/user_guides/dflow/dflow_dev/python/quick_start.md：环境要求"当前仅支持Python3.11"改为3.12 - docs/zh/user_guides/dflow/dflow_dev/python/appendices.md：UDF工程创建命令 python3.11 改为 python3.12 - examples/dflow/python/README.md / README_en.md：python版本要求及7条样例运行命令更新为3.12 - examples/dflow/python/udf_py_ws_sample/CMakeLists.txt：find_package(Python3 3.11 EXACT ...) 改为3.12，避免3.12环境下样例构建失败 ## 变更类型 - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [x] 📝 文档内容更新 ## 关联的Issue ## 如何测试 1. 纯文档修改 + 样例CMakeLists一行版本号变更，不在主构建路径 2. grep -r "3\.11" 确认dflow相关文档及样例无3.11残留 3. 本地pre-commit检查全部通过 ## 核对清单 - [x] 我的代码遵循了项目的代码风格 - [x] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [x] 我在标题中使用了合适的类型标签（如：feat:, fix:） - [x] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 无 See merge request: cann/ge!4686 | 14 天前 | |
fix: replace Chinese log messages with English in examples Co-authored-by: wangyuchen<wangyuchen38@huawei.com> # message auto-generated for no-merge-commit merge: !4883 merge fix/example_log into develop fix: replace Chinese log messages with English in examples Created-by: yuchen97 Commit-by: wangyuchen Merged-by: cann-robot Description: ## Description Replace Chinese log/print messages with English across all examples/ subdirectories to comply with the "no Chinese in logs" rule. Also fix one implicit string concatenation bug (missing space) and improve the English fluency of a previously awkward translation. ## Changes ### examples/es/ (183 issues, 30 files) - C++ main.cpp files (14 subdirs): "GE 初始化失败" → "GE initialization failed", "执行结束" → "Execution completed", "错误: 未知命令" → "Error: unknown command" - Python run_graph() (16 files): all Chinese print statements replaced with fluent English ("图运行成功" → "Graph executed successfully", "清理GE环境" → "Cleaning up GE environment", etc.) - hccl_ep/hccl_tp: "单卡模式"/"多卡模式" → "Single-card mode"/"Multi-card mode" ### examples/fusion_pass/ (68 issues, 12 files) - RuntimeError messages: ES API missing prompts translated from Chinese to English with proper README section references - Pass registration messages: "已注册" → "registered", "请通过 ASCEND_GE_PY_PASS_PATH 指向本文件" → "Please add this file to ASCEND_GE_PY_PASS_PATH" (improved translation per review feedback) - Graph base pass and pattern base pass: all Chinese print/log replaced ### examples/multi_stream_autotune/ (73 issues, 3 files) - ge_ms_autotune.py: ~110 Chinese log/error/print messages replaced; header and column labels in output table anglicized; docstrings updated - sample_run.py: Chinese comments and print statements replaced - README.md / README_en.md: example output section updated to match new English outputs - Fixed missing space bug in find_compiled_om() string concatenation ### examples/offline_compile_run/ (70 issues, 10 files) - C++ files: all std::cerr/std::cout Chinese messages replaced ("失败" → "failed", "初始化成功" → "initialized successfully", etc.) - Python files: all Chinese print/f-string messages replaced with English equivalents ## Change Statistics - **56 files** modified - **467 insertions**, **442 deletions** - **394 Chinese log messages** converted to English across 4 module directories ## Change Type - [ ] 🐛 Bug fix - [ ] ✨ New feature - [ ] 💄 Code style update - [ ] ♻️ Refactoring - [ ] 📦 Build process - [x] 📝 Documentation / example update ## How to Test 1. Build any example under examples/ and verify all output messages are in English 2. Check examples/multi_stream_autotune/ outputs for proper formatting ## Checklist - [x] My code follows the project's code style - [x] I have self-tested the changes - [x] I have updated related documentation - [x] I have used appropriate type label in the title - [x] I have read and followed the contributing guidelines See merge request: cann/ge!4883 | 6 天前 | |
fix: replace Chinese log messages with English in examples Co-authored-by: wangyuchen<wangyuchen38@huawei.com> # message auto-generated for no-merge-commit merge: !4883 merge fix/example_log into develop fix: replace Chinese log messages with English in examples Created-by: yuchen97 Commit-by: wangyuchen Merged-by: cann-robot Description: ## Description Replace Chinese log/print messages with English across all examples/ subdirectories to comply with the "no Chinese in logs" rule. Also fix one implicit string concatenation bug (missing space) and improve the English fluency of a previously awkward translation. ## Changes ### examples/es/ (183 issues, 30 files) - C++ main.cpp files (14 subdirs): "GE 初始化失败" → "GE initialization failed", "执行结束" → "Execution completed", "错误: 未知命令" → "Error: unknown command" - Python run_graph() (16 files): all Chinese print statements replaced with fluent English ("图运行成功" → "Graph executed successfully", "清理GE环境" → "Cleaning up GE environment", etc.) - hccl_ep/hccl_tp: "单卡模式"/"多卡模式" → "Single-card mode"/"Multi-card mode" ### examples/fusion_pass/ (68 issues, 12 files) - RuntimeError messages: ES API missing prompts translated from Chinese to English with proper README section references - Pass registration messages: "已注册" → "registered", "请通过 ASCEND_GE_PY_PASS_PATH 指向本文件" → "Please add this file to ASCEND_GE_PY_PASS_PATH" (improved translation per review feedback) - Graph base pass and pattern base pass: all Chinese print/log replaced ### examples/multi_stream_autotune/ (73 issues, 3 files) - ge_ms_autotune.py: ~110 Chinese log/error/print messages replaced; header and column labels in output table anglicized; docstrings updated - sample_run.py: Chinese comments and print statements replaced - README.md / README_en.md: example output section updated to match new English outputs - Fixed missing space bug in find_compiled_om() string concatenation ### examples/offline_compile_run/ (70 issues, 10 files) - C++ files: all std::cerr/std::cout Chinese messages replaced ("失败" → "failed", "初始化成功" → "initialized successfully", etc.) - Python files: all Chinese print/f-string messages replaced with English equivalents ## Change Statistics - **56 files** modified - **467 insertions**, **442 deletions** - **394 Chinese log messages** converted to English across 4 module directories ## Change Type - [ ] 🐛 Bug fix - [ ] ✨ New feature - [ ] 💄 Code style update - [ ] ♻️ Refactoring - [ ] 📦 Build process - [x] 📝 Documentation / example update ## How to Test 1. Build any example under examples/ and verify all output messages are in English 2. Check examples/multi_stream_autotune/ outputs for proper formatting ## Checklist - [x] My code follows the project's code style - [x] I have self-tested the changes - [x] I have updated related documentation - [x] I have used appropriate type label in the title - [x] I have read and followed the contributing guidelines See merge request: cann/ge!4883 | 6 天前 | |
fix: precommit整改 Co-authored-by: yelongjian<yelongjian1@huawei.com> # message auto-generated for no-merge-commit merge: !3726 merge dev-precommit into develop fix: precommit整改 Created-by: yelongjian Commit-by: yelongjian Merged-by: cann-robot Description: # Pull Request ## 描述 precommit整改 ## 变更类型 请选择本次引入的变更类型： <!-- [x] 表示选中 --> - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [x] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [ ] 📝 文档内容更新 ## 关联的Issue <!-- 如果这个PR是为了解决特定的Issue，请在当前页面的右侧'关联Issue'部分添加相应Issue链接，并勾选'合并后关闭已关联的 Issue'选项。 --> ## 如何测试 描述测试此变更的步骤和前提条件： 1.NA ## 核对清单 <!-- [x] 表示选中 --> - [x] 我的代码遵循了项目的代码风格 - [x] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [x] 我在标题中使用了合适的类型标签（如： feat:, fix:） - [x] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 在此添加任何其他关于本次 PR 的说明。 See merge request: cann/ge!3726 | 2 个月前 | |
fix: replace Chinese log messages with English in examples Co-authored-by: wangyuchen<wangyuchen38@huawei.com> # message auto-generated for no-merge-commit merge: !4883 merge fix/example_log into develop fix: replace Chinese log messages with English in examples Created-by: yuchen97 Commit-by: wangyuchen Merged-by: cann-robot Description: ## Description Replace Chinese log/print messages with English across all examples/ subdirectories to comply with the "no Chinese in logs" rule. Also fix one implicit string concatenation bug (missing space) and improve the English fluency of a previously awkward translation. ## Changes ### examples/es/ (183 issues, 30 files) - C++ main.cpp files (14 subdirs): "GE 初始化失败" → "GE initialization failed", "执行结束" → "Execution completed", "错误: 未知命令" → "Error: unknown command" - Python run_graph() (16 files): all Chinese print statements replaced with fluent English ("图运行成功" → "Graph executed successfully", "清理GE环境" → "Cleaning up GE environment", etc.) - hccl_ep/hccl_tp: "单卡模式"/"多卡模式" → "Single-card mode"/"Multi-card mode" ### examples/fusion_pass/ (68 issues, 12 files) - RuntimeError messages: ES API missing prompts translated from Chinese to English with proper README section references - Pass registration messages: "已注册" → "registered", "请通过 ASCEND_GE_PY_PASS_PATH 指向本文件" → "Please add this file to ASCEND_GE_PY_PASS_PATH" (improved translation per review feedback) - Graph base pass and pattern base pass: all Chinese print/log replaced ### examples/multi_stream_autotune/ (73 issues, 3 files) - ge_ms_autotune.py: ~110 Chinese log/error/print messages replaced; header and column labels in output table anglicized; docstrings updated - sample_run.py: Chinese comments and print statements replaced - README.md / README_en.md: example output section updated to match new English outputs - Fixed missing space bug in find_compiled_om() string concatenation ### examples/offline_compile_run/ (70 issues, 10 files) - C++ files: all std::cerr/std::cout Chinese messages replaced ("失败" → "failed", "初始化成功" → "initialized successfully", etc.) - Python files: all Chinese print/f-string messages replaced with English equivalents ## Change Statistics - **56 files** modified - **467 insertions**, **442 deletions** - **394 Chinese log messages** converted to English across 4 module directories ## Change Type - [ ] 🐛 Bug fix - [ ] ✨ New feature - [ ] 💄 Code style update - [ ] ♻️ Refactoring - [ ] 📦 Build process - [x] 📝 Documentation / example update ## How to Test 1. Build any example under examples/ and verify all output messages are in English 2. Check examples/multi_stream_autotune/ outputs for proper formatting ## Checklist - [x] My code follows the project's code style - [x] I have self-tested the changes - [x] I have updated related documentation - [x] I have used appropriate type label in the title - [x] I have read and followed the contributing guidelines See merge request: cann/ge!4883 | 6 天前 | |
fix: replace Chinese log messages with English in examples Co-authored-by: wangyuchen<wangyuchen38@huawei.com> # message auto-generated for no-merge-commit merge: !4883 merge fix/example_log into develop fix: replace Chinese log messages with English in examples Created-by: yuchen97 Commit-by: wangyuchen Merged-by: cann-robot Description: ## Description Replace Chinese log/print messages with English across all examples/ subdirectories to comply with the "no Chinese in logs" rule. Also fix one implicit string concatenation bug (missing space) and improve the English fluency of a previously awkward translation. ## Changes ### examples/es/ (183 issues, 30 files) - C++ main.cpp files (14 subdirs): "GE 初始化失败" → "GE initialization failed", "执行结束" → "Execution completed", "错误: 未知命令" → "Error: unknown command" - Python run_graph() (16 files): all Chinese print statements replaced with fluent English ("图运行成功" → "Graph executed successfully", "清理GE环境" → "Cleaning up GE environment", etc.) - hccl_ep/hccl_tp: "单卡模式"/"多卡模式" → "Single-card mode"/"Multi-card mode" ### examples/fusion_pass/ (68 issues, 12 files) - RuntimeError messages: ES API missing prompts translated from Chinese to English with proper README section references - Pass registration messages: "已注册" → "registered", "请通过 ASCEND_GE_PY_PASS_PATH 指向本文件" → "Please add this file to ASCEND_GE_PY_PASS_PATH" (improved translation per review feedback) - Graph base pass and pattern base pass: all Chinese print/log replaced ### examples/multi_stream_autotune/ (73 issues, 3 files) - ge_ms_autotune.py: ~110 Chinese log/error/print messages replaced; header and column labels in output table anglicized; docstrings updated - sample_run.py: Chinese comments and print statements replaced - README.md / README_en.md: example output section updated to match new English outputs - Fixed missing space bug in find_compiled_om() string concatenation ### examples/offline_compile_run/ (70 issues, 10 files) - C++ files: all std::cerr/std::cout Chinese messages replaced ("失败" → "failed", "初始化成功" → "initialized successfully", etc.) - Python files: all Chinese print/f-string messages replaced with English equivalents ## Change Statistics - **56 files** modified - **467 insertions**, **442 deletions** - **394 Chinese log messages** converted to English across 4 module directories ## Change Type - [ ] 🐛 Bug fix - [ ] ✨ New feature - [ ] 💄 Code style update - [ ] ♻️ Refactoring - [ ] 📦 Build process - [x] 📝 Documentation / example update ## How to Test 1. Build any example under examples/ and verify all output messages are in English 2. Check examples/multi_stream_autotune/ outputs for proper formatting ## Checklist - [x] My code follows the project's code style - [x] I have self-tested the changes - [x] I have updated related documentation - [x] I have used appropriate type label in the title - [x] I have read and followed the contributing guidelines See merge request: cann/ge!4883 | 6 天前 | |
feat: add Python ONNX graph callbacks Co-authored-by: gentle-knight<522025150054@smail.nju.edu.cn> # message auto-generated for no-merge-commit merge: !4583 merge feat/onnx-plugin-python-pr4-graph-callbacks-submit into develop feat: add Python ONNX graph callbacks Created-by: gentle-knight Commit-by: gentle-knight Merged-by: cann-robot Description: ## Pull Request ### 描述 将 Python ONNX Plugin 的 Graph callback 接入现有 ONNX parser，合并支持一对多图展开和子图后处理。复用现有 GraphBuilder、ParserUtils::ExpandOneToManyGraph 及 ParseSubgraphPostFn/ParseSubgraphFuncV2，不新增 onnx_node.py、Operator pybind 或第二套 parser 流程。 ### 变更类型 - [ ] 🐛 Bug 修复 - [x] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [ ] 📝 文档内容更新 ### 关联的Issue 无。 ### 如何测试 1. Python registry/bridge 测试：39 项通过。 2. ge_python_onnx_plugin_bridge 增量构建通过。 3. 新增 C++ bridge UT 与 ONNX parser ST 源文件编译通过。 4. parser ST 覆盖真实 ONNX 一对多展开及 If 子图 callback；本地最终运行受 CANN 9.2 开发包缺失符号影响，交由远程 CI 验证。 ### 核对清单 - [x] 我的代码遵循了项目的代码风格 - [x] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [x] 我在标题中使用了合适的类型标签（如： feat:, fix:） - [x] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ### 其他信息 本 PR 基于已合入 PR3 的最新 develop，仅包含一个代码 commit，代码增量为 523 行新增、4 行删除。设计与评审记录已更新在本地文档，未混入代码 commit。 See merge request: cann/ge!4583 | 19 天前 | |
docs: 【直播作业】填写 Recommendation 最优多流配置-v3 (#516) Co-authored-by: nimj<mengjunni00@gmail.com> # message auto-generated for no-merge-commit merge: !4435 merge develop into develop docs: 【直播作业】填写 Recommendation 最优多流配置-v3 (#516) Created-by: nimj Commit-by: nimj Merged-by: cann-robot Description: ## 备注 首次pull request（https://gitcode.com/cann/ge/merge_requests/4433） 使用邮箱错误，cla-check失败，重新提交 ## 描述 【直播作业】填写 Recommendation(DCN v2)样例的最优多流增强参数。 在 CANNLab(Ascend 910C)环境、CANN 社区版 9.2.0-beta.1 下,对 ge.autoMultistreamParallelMode 的 19 个配置(Base + cv + LoadBalance:N + MainStream:N)进行寻优,主评价指标为 Average ExecuteGraphWithStreamAsync latency,最优配置为 **MainStream:9**(0.113322 ms,较 Base 0.189378 ms **降低约 40%**)。 本次变更将 examples/recommendation/README.md 与 README_en.md 中的 <待填写>/<to-be-determined> 替换为 MainStream:9,中英文结论一致。 ## 变更类型 - [x] 📝 文档内容更新 ## 关联的 Issue #516 ## 如何测试 **环境**： - CANNLab:Ascend 910C(Ascend910_9362,单 NPU 双 die,64G HBM),驱动 npu-smi 25.5.5 - CANN 社区版 9.2.0-beta.1(Weekly,A3 系列,AArch64,openEuler,离线安装) - 代码分支:develop **测试环境截图**：  **CANN版本**  **步骤**(每个配置完全一致,仅 --multiStreamParallelMode 变化): bash cd examples/recommendation/build ./recomand_exec --runs=100 --batchSize=128 --multiInstanceNum=1 --multiStreamParallelMode=<模式> 1. Base 配置不传 --multiStreamParallelMode;候选分别传入 cv / LoadBalance:N / MainStream:N 2. 前 10 个成功任务预热不计入,后 90 个成功任务计算算术平均时延 3. 主评价指标:Average ExecuteGraphWithStreamAsync latency(ExecuteGraphWithStreamAsync + aclrtSynchronizeStream) 4. 每个配置日志均显示 Success count: 100,结果有效 ## 核对清单 - [x] 我的代码遵循了项目的代码风格 - [x] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [x] 我在标题中使用了合适的类型标签(docs:) - [x] 我已经详细阅读了贡献指南(CONTRIBUTING.md),并遵守了其中的所有规定 ## 其他信息 ### 完整测试结果 | 配置角色 | 多流配置 | 主评价指标平均耗时(ms) | 正式统计任务数 | |---|---|---|---| | Base 配置 | 未配置多流参数 | 0.189378(复测 0.189767) | 90 | | 候选配置 | cv | 0.171900 | 90 | | 候选配置 | LoadBalance:2 | 0.164244 | 90 | | 候选配置 | LoadBalance:4 | 0.146511 | 90 | | 候选配置 | LoadBalance:8 | 0.152900 | 90 | | 候选配置 | LoadBalance:16 | 0.144589 | 90 | | 候选配置 | MainStream:2 | 0.148067 | 90 | | 候选配置 | MainStream:4 | 0.124722 | 90 | | 候选配置 | MainStream:6 | 0.120200 | 90 | | 候选配置 | MainStream:7 | 0.118400 | 90 | | 候选配置 | MainStream:8 | 0.117856 | 90 | | **最优配置** | **MainStream:9** | **0.113322** | 90 | | 候选配置 | MainStream:10 | 0.118489 | 90 | | 候选配置 | MainStream:11 | 0.119244 | 90 | | 候选配置 | MainStream:12 | 0.112567 | 90 | | 候选配置 | MainStream:13 | 0.115256 | 90 | | 候选配置 | MainStream:14 | 0.121322 | 90 | | 候选配置 | MainStream:16 | 0.124833 | 90 | ### 最优配置结论 text ge.autoMultistreamParallelMode=MainStream:9 --multiStreamParallelMode=MainStream:9 - Base: 0.189378 ms(复测 0.189767 ms,稳定) - 最优 MainStream:9: 0.113322 ms(复测 0.113233 / 0.114222 ms,波动 <1%,稳定最优) - 时延降低约 40%(0.1894 → 0.1133 ms) > 说明: MainStream:12 初测 0.112567 ms 略低于 MainStream:9,但两次复测为 0.117122 / 0.117811 ms(回落),初测值为波动低点;MainStream:9 三次测量均稳定在 0.113~0.114 ms,故选 MainStream:9 为最优配置。 ### 关键日志(复核用) Base 配置: Run 100 inferences in 1.21777 seconds. Success count: 100 Average ExecuteGraphWithStreamAsync latency: 0.189378 ms 最优配置 MainStream:9(三次测量): Run 100 inferences in 1.99051 seconds. Success count: 100 Average ExecuteGraphWithStreamAsync latency: 0.113322 ms Run 100 inferences in 1.87045 seconds. Success count: 100 Average ExecuteGraphWithStreamAsync latency: 0.113233 ms Run 100 inferences in 1.27304 seconds. Success count: 100 Average ExecuteGraphWithStreamAsync latency: 0.114222 ms **测试截图**  See merge request: cann/ge!4435 | 29 天前 | |
【PR】: 新增中英文跳转链接 Co-authored-by: sophia1213<sophie.chen@huawei.com> # message auto-generated for no-merge-commit merge: !4750 merge develop into develop 【PR】: 新增中英文跳转链接 Created-by: sophia1213 Commit-by: sophia1213 Merged-by: cann-robot Description: # Pull Request ## 描述 RAEDME以及一级文件夹根目录添加中英文跳转链接。 ## 变更类型 请选择本次引入的变更类型： <!-- [x] 表示选中 --> - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [x] 📝 文档内容更新 ## 关联的Issue 不涉及 ## 如何测试 根据最新资料进行测试 ## 核对清单 <!-- [x] 表示选中 --> - [ ] 我的代码遵循了项目的代码风格 - [ ] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [ ] 我在标题中使用了合适的类型标签（如： feat:, fix:） - [ ] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 在此添加任何其他关于本次 PR 的说明。 See merge request: cann/ge!4750 | 9 天前 | |
【PR】: 新增中英文跳转链接 Co-authored-by: sophia1213<sophie.chen@huawei.com> # message auto-generated for no-merge-commit merge: !4750 merge develop into develop 【PR】: 新增中英文跳转链接 Created-by: sophia1213 Commit-by: sophia1213 Merged-by: cann-robot Description: # Pull Request ## 描述 RAEDME以及一级文件夹根目录添加中英文跳转链接。 ## 变更类型 请选择本次引入的变更类型： <!-- [x] 表示选中 --> - [ ] 🐛 Bug 修复 - [ ] ✨ 新功能 - [ ] 💄 代码风格更新（格式化，局部变量） - [ ] ♻️ 重构（既不修复错误也不增加功能的代码变动） - [ ] 📦 构建过程或辅助工具的变动 - [x] 📝 文档内容更新 ## 关联的Issue 不涉及 ## 如何测试 根据最新资料进行测试 ## 核对清单 <!-- [x] 表示选中 --> - [ ] 我的代码遵循了项目的代码风格 - [ ] 我已对代码进行了自测 - [x] 我已更新了相关的文档 - [ ] 我在标题中使用了合适的类型标签（如： feat:, fix:） - [ ] 我已经详细阅读了贡献指南（CONTRIBUTING.md），并遵守了其中的所有规定，包括但不限于commit message的格式、无效commit的合并等 ## 其他信息 在此添加任何其他关于本次 PR 的说明。 See merge request: cann/ge!4750 | 9 天前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 29 天前 | ||
| 2 个月前 | ||
| 5 天前 | ||
| 14 天前 | ||
| 6 天前 | ||
| 6 天前 | ||
| 2 个月前 | ||
| 6 天前 | ||
| 6 天前 | ||
| 19 天前 | ||
| 29 天前 | ||
| 9 天前 | ||
| 9 天前 |