x5-qat-deploy
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
编排 X5 horizon_plugin_pytorch calibration、QAT、定点转换与 Plugin 编译;当用户有可训练 PyTorch 模型、数据和浮点基线,希望得到 March.BAYES_E 的 .hbm/.hbir 及指标闭环时使用。明确排除 HAT,且不把 QAT 自动交给 hb_mapper makertbin。
In this repository59 other files it gives its agents.
- bsp-bootloader-buildSkill
- bsp-deb-buildSkill
- bsp-env-setupSkill
- bsp-image-buildSkill
- bsp-kernel-buildSkill
- bsp-rootfs-customSkill
- bsp-source-syncSkill
- bsp-s-seriesSkill
- hmct-workflowSkill
- horizon-routerSkill
- ucpSkill
- x5-accuracy-diagnosticsSkill
- x5-board-monitorSkill
- x5-bpu-python-apiSkill
- x5-calibration-data-prepareSkill
- x5-consistency-diagnosticsSkill
- x5-environment-installSkill
- x5-environment-probeSkill
- x5-environment-setupSkill
- x5-model-diagnosticsSkill
- x5-model-preflightSkill
- x5-performance-diagnosticsSkill
- x5-ptq-compileSkill
- x5-ptq-config-authoringSkill
- x5-ptq-deploySkill
- x5-qat-adaptationSkill
- x5-qat-compileSkill
- x5-qat-trainingSkill
- x5-routerSkill
- x5-runtime-cpp-inferSkill
- x5-runtime-deploySkill
- x5-runtime-perf-evalSkill
- rdk-accessoriesSkill
- rdk-board-delegateSkill
- rdk-board-knowledgeSkill
- rdk-camera-setupSkill
- rdk-command-manualSkill
- rdk-diagnosticSkill
- rdk-docs-referenceSkill
- rdk-ecosystemSkill
- rdk-embodied-lerobotSkill
- rdk-gpio-40pinSkill
- rdk-hardwareSkill
- rdk-headless-modeSkill
- rdk-llm-deploymentSkill
- rdk-log-forensicsSkill
- rdk-memory-auditSkill
- rdk-model-benchmarkSkill
- rdk-model-deploySkill
- rdk-model-zooSkill
- rdk-multimediaSkill
- rdk-network-remoteSkill
- rdk-peripheral-cookbookSkill
- rdk-source-mapSkill
- rdk-system-configSkill
- rdk-system-maintainSkill
- rdk-tros-setupSkill
- rdk-vision-pipelineSkill
- d-robotics-pack-installerSkill
The file
Files
X5 Plugin QAT 工作流
目标与边界
QAT 合同固定为 March.BAYES_E → adaptation → calibration/QAT → convert → check_model → compile_model/export_hbir。Plugin .hbm/.hbir 与 OE Mapper PTQ .bin 是不同产物,不改后缀、不自动互转。
输入合同
- 可训练 PyTorch 模型和可复现构建入口。
- 训练/校准/验证数据、浮点权重、浮点指标和评价代码。
- Plugin/PyTorch/Python/GPU 环境快照、example inputs、输出目录和预算。
- 目标指标、最大训练成本和检查点覆盖策略。
前置检查
- 目标芯片是 X5,源码明确使用
March.BAYES_E;手册 quick start 中的March.BAYES示例必须替换并验证。 - HAT package、config、Trainer、registry、Model Zoo 与
tools/compile_perf.py均不得进入流程。 - 先复现浮点基线;无法复现时不得用 QAT 指标宣称改善。
- 训练环境、数据版本和随机种子可记录;输出使用新 attempt 目录。
执行步骤
x5-qat-adaptation:设置 march、量化边界、算子适配和 prepare。x5-qat-training:记录 calibration、QAT 和 quantized 各阶段指标与检查点。x5-qat-compile:check_model后生成.hbm或.hbir,保存编译证据。- 仅在实际 Runtime/模型信息证明兼容后交接
x5-runtime-deploy;证据不足保持blocked。
产物与完成标准
- 浮点、calibration、QAT、quantized 指标来自同一评测合同。
- 源码检查证明
March.BAYES_E,且无 HAT/hb_mapper makertbin混用。 - 检查点、定点模型、
check_model日志和.hbm/.hbir哈希完整。 - 编译成功不等于 Runtime 成功;部署兼容性和板端正确性必须单独验证。
风险与确认
训练、生成模型和安装用户依赖为中风险;覆盖检查点、共享环境或长时间训练前必须展示成本与恢复方式并确认。
失败与交接
- 精度掉点 →
x5-accuracy-diagnostics。 - 定点/编译不一致 →
x5-consistency-diagnostics。 - 环境问题 →
x5-environment-setup。 - 同一训练/编译策略最多两次;第二次失败后停止自动试参。
按需参考
.drobotics/platforms/x5/policies/compatibility.md_sources/plugin/source/quick_start/quick_start.ipynb.txt
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

