mindspore-ai/mindspore-lite

open-source-model-migration

把开源算法模型适配到 MindSpore Lite 部署管线：按网络结构拆分导出 ONNX、ONNX Runtime 推理验证、ONNX→MindIR 转换、MindSpore Lite 推理实现，并交付文档与常见问题。用户想把某个开源模型迁移到 MSLite 部署时调用。

Idioma do texto original: chinês

precision-troubleshooting

MindSpore Lite MindIR模型精度问题定位技能。覆盖从CANN Profiling对比分析定位可疑算子、配置算子Dump、到最终对比Dump数据确定精度差异根因算子的全流程。

Idioma do texto original: chinês

tensor-parallel-deployment

开源 LLM 模型的多卡张量并行部署：Megatron 风格权重分片导出 → ONNX→MindIR 转换（离线 acl / GE online 双路径）→ 多进程 HCCL 推理。覆盖 1p/2p/4p 三种模式，含 Custom 算子（AllReduce/Scatter/RMSNorm 等）开发与通信机制、300I Duo 与 800I A2 差异、已知限制与修复方案。用户想把模型部署到多卡/多芯 Ascend 推理时调用。

Idioma do texto original: chinês

performance-optimization

MindSpore Lite（Ascend）模型性能优化总攻略。做基线/profiling、融合算子改写、推理免拷贝、PTQ int8 量化、精度对齐与归档时调用。本文为总览与索引，细化策略见 references/。

Idioma do texto original: chinês

onnx-model-conversion-and-deployment

MindSpore Lite云侧推理 Ascend 后端离线转换（ONNX → MindIR）与推理部署全流程。覆盖固定 shape、动态分档、纯动态 shape 的转换策略，以及 MindIR 推理验证与部署注意事项。

Idioma do texto original: chinês

lite-build

Build configuration, CMake options, cross-compilation and packaging. Use when building MindSpore Lite, configuring CMake, cross-compiling for ARM/iOS/MCU, packaging release archives, or troubleshooting build errors.

Idioma do texto original: inglês

lite-converter

Model conversion pipeline, parser development, optimization passes and quantization. Use when converting models to .ms, writing parser code, implementing optimizer passes, or configuring quantization.

Idioma do texto original: inglês

lite-debug-test

Debugging, unit testing, benchmarking and performance analysis. Use when running gtest, benchmark tools, profiling latency or accuracy, diagnosing operator precision issues, delegate fallback, or memory leaks.

Idioma do texto original: inglês

lite-device-side-infer

Device-side inference with LiteRT, NNACL and hardware delegates. Use for mobile/IoT inference, Android/iOS integration, NPU/GPU/CoreML delegates, Micro codegen for MCU, on-device training, or C/C++/Java/Python API usage with .ms models.

Idioma do texto original: inglês

lite-kernel-dev

Operator and kernel development, NNACL, delegates, custom kernel registration. Use when adding operators, implementing NNACL kernels, writing delegate adapters (NPU/CoreML/Ascend), registering custom kernels, or modifying operator schema.

Idioma do texto original: inglês

clean-code-check

改完或 review MindSpore Lite 的 C++/Python/Shell/CMake 代码时用。先跑 pre-push（8 个 lint 全自动），再按 30 秒快速清单逐项过——三类硬指标（CCN≤19 / NLOC≤50 / 入参≤5）+ 指针/边界/逻辑/异常/接口契约等 lint 抓不到的语义问题 + 涉及外部数据时的安全编码。深度参考 clean-code-guidelines.md。

Idioma do texto original: chinês