Hammer：一体化的模型压缩和 NAS 引擎框架.pdf

《Hammer：一体化的模型压缩和 NAS 引擎框架.pdf》由会员分享，可在线阅读，更多相关《Hammer：一体化的模型压缩和 NAS 引擎框架.pdf（46页珍藏版）》请在三个皮匠报告上搜索。

1、名快手Hammer!:A UnifiedFramework of ModelCompression and NASSpeaker: Xiufeng Xie， Hongmin XuAI Platform， Seattle Al lab，and FeDA lab KwaiKey Contributors: Hongmin Xu Xiufeng Xie Jiianchao TanYiGuo Huan Yuan Jixiang Li Xiangru Lian and JiLiu#page#名快手ContributorsKey contributors#page#why Do We Need DNN M

2、odel Compression？名快手Speech recognitionBeauty photosFace unlock共国：1悦璃Online recommendation (iinference）#page#Goals in Model Compression名快手Model compressionAccuracyComputation efficiencyEnergy efficiency#page#Energy 8 Computing名快手Cost A LotExample: run an Al application that costs 100M FlopsOn ServerO

3、n Phone8Cost 1000 （5） per dayCost 1.8M （5） per daySource: 1 and assuming 300M DAU and 100 videos/user#page#名快手However. Model Size ls Not The Whole Story10%Model Size/FlopsEnergyLatencyDepend on the hardware#page#Model Compression Tools名快手ToolToolUnifiedModelModelNAS forHardwareNamePruningAuthorFrame

4、workQuantizationAwarenessCompressionKwaiXXXPocketFlowTencentSXXINNXMicrosoftX一DistillerIntelXXXPaddlePaddleBaiduXXXXGoogleXTensorflow LiteXXAIMETXQualcommXSXCondensaNvidiaHammer:JointPruning + Quantization +NASOthers:PruningQuantization#page#名快手Ubiquitous AI optimization with an allin-one framework电

5、中中AccuracymaxS Latency toleranceApplication requirementHardware resource budgetS Resource budgetAdd as many consttraints as the user wants#page#名快手Hammer! Supported1Compression Strategies88888aooo2（8oPruning（剪枝）（量化）QuantizationNeural architecture search时可电建中（NAS，神经结构搜索）#page#名快手Hammer! ls GPU-Hardwa

6、re-AwareSearch for a DNN structure that best fits GPU hardwareModular booster#input channelis multiple of N三贸#output channelis multiple ofNN=8LatencyOptimize DNNs running latency on the target GPUProfilingLatencyOptimizerModelEnergyOptimize DNNsenergy cost on the target GPUProfilingEnergyOptimizerMo