llm, qnn, qualcomm
源码：https://github.com/UbiquitousLearning/mllm
1.qnn后端的接入
这里只是给一个核心的思路，不涉及具体的代码实现。
前言：
- qualcomm htp后端，因为支持的数据类型有限，int8/int16/float16，如果要用int数据类型加速，需要对模型进行量化。mllm中使用的是int8，但是不是整个整个网络使用int8，而是部分使用，同时qnn npu推理时是cpu+npu混合的。
实现：
- 因为qualcomm sdk使用方式的限制，没有单独使用qualcomm op进行计算的方式，需要构建graph。所以mllm中将decoder部分拆成几个qnn graph。具体代码如下：
Backend::global_backends[device_]->onSetUpStart(inputs_vec, outputs_vec, getUinqueName());// for xnnpack currentlyfor (auto &i : inputs) {i.uuid() = inputs[0].module()->activation_tensors[i.name()]->uuid();}auto outputs = Forward(inputs, anyArgs);for (auto &output : outputs) {outputs_vec.push_back(inputs[0].module()->activation_tensors[output.name()]);}Backend::global_backends[device_]->onSetUpEnd(inputs_vec, outputs_vec, getUinqueName());
qnnbackend.onsetupstart中会初始化QnnModel
qnnModels_.push_back(qnn_wrapper_api::QnnModel());// create qnn context, assign context to qnn memory managerif (StatusCode::SUCCESS != this->createContext()) {this->reportError("Context Creation failure");}
#ifdef QNN_ARMauto qnnMM = std::static_pointer_cast<QNNMemoryManager>(mem_manager_);qnnMM->setQnnInterfaceAndContext(m_context);
#endif// initialize qnn graph info, set graph info, graph count// NOTE: currently not using itQnnHtpGraph_CustomConfig_t customConfig;// customConfig.option = QNN_HTP_GRAPH_CONFIG_OPTION_NUM_HVX_THREADS;// customConfig.numHvxThreads = 4; // set a number. MAX = number of HVX HW blocks for that SoCcustomConfig.option = QNN_HTP_GRAPH_CONFIG_OPTION_VTCM_SIZE;customConfig.vtcmSizeInMB = 8;QnnGraph_Config_t graphConfig;graphConfig.option = QNN_GRAPH_CONFIG_OPTION_CUSTOM;graphConfig.customConfig = &customConfig;const QnnGraph_Config_t *pGraphConfig[] = {&graphConfig, NULL};const QnnGraph_Config_t **graphConfigs = pGraphConfig;m_graphConfigsInfoCount = 1;qnn_wrapper_api::ModelError_t err = qnn_wrapper_api::getQnnGraphConfigFromInfo(graphName.c_str(), (const qnn_wrapper_api::GraphConfigInfo_t **)m_graphConfigsInfo, m_graphConfigsInfoCount, graphConfigs);if (err != qnn_wrapper_api::MODEL_NO_ERROR) {this->reportError("Graph Config Info failure");}err = qnnModels_[qnnModelIndex_].initialize(m_backendHandle,m_qnnFunctionPointers.qnnInterface,m_context,graphName.c_str(),m_debug,DO_GRAPH_NODE_VALIDATIONS,graphConfigs);if (err != qnn_wrapper_api::MODEL_NO_ERROR) {this->reportError("Graph Initialization failure: " + graphName);}
后续再通过op.setup方法往QnnModel中添加tensor和op，如QNNLinearINT8
graphAddNode(name() + ".linearint8", "Conv2d", {inputs[0]->name(), weight_.name()}, matmulOut, params_InceptionV3_InceptionV3_Conv2d_1a_3x3_Conv2D);
2. other
这都是qualcomm sdk中op不支持单op后端支持，必须要构建model来调用。不友好。