Botframework Orchestrator多语言模型部署Azure Sites报内存分配错误

该问题似乎仅出现在被重命名为model.onnx的pretrained.20210205.microsoft.dte.00.06.unicoder_multilingual.onnx预训练模型上，若使用英文模型则运行一切正常。

请问是否有人成功将替代NLP Dispatch的新版Orchestrator部署到Azure Sites上运行？我参照迁移示例操作后，本地使用模拟器或ngrok运行均正常，但部署到Azure Sites后无法读取模型。

EXCEPTION THROWN - utility_onnx::OnnxUtility::InitOnnxSession(): e.what()=Load model from D:\home\site\wwwroot\CognativeModels\model\model.onnx failed:bad allocation, FILE=D:\a\1\s\oc\utility\OnnxUtility.h, LINE=117
EXCEPTION THROWN - OC - EmbedderBase::EmbedderBase(json const& config, const string onnxVocabFileDefault, const string onnxModelFileDefault): e.what()=Load model from D:\home\site\wwwroot\CognativeModels\model\model.onnx failed:bad allocation, FILE=D:\a\1\s\oc\EmbedderBase.cc, LINE=57
fail: Microsoft.Bot.Builder.Integration.AspNet.Core.BotFrameworkHttpAdapter[0]
[OnTurnError] unhandled error : Failed to find or load Model with path D:\home\site\wwwroot\CognativeModels\model
System.InvalidOperationException: Failed to find or load Model with path D:\home\site\wwwroot\CognativeModels\model
---> System.ApplicationException: Load model from D:\home\site\wwwroot\CognativeModels\model\model.onnx failed:bad allocation
at Microsoft.BotFramework.Orchestrator.Orchestrator..ctor(String baseModelConfigOrPath)
at Microsoft.Bot.Builder.AI.Orchestrator.OrchestratorRecognizer.b__39_0(String path)
--- End of inner exception stack trace ---
at Microsoft.Bot.Builder.AI.Orchestrator.OrchestratorRecognizer.b__39_0(String path)
at System.Collections.Concurrent.ConcurrentDictionary`2.GetOrAdd(TKey key, Func`2 valueFactory)
at Microsoft.Bot.Builder.AI.Orchestrator.OrchestratorRecognizer.InitializeModel()
at Microsoft.Bot.Builder.AI.Orchestrator.OrchestratorRecognizer.RecognizeAsync(DialogContext dc, Activity activity, CancellationToken cancellationToken, Dictionary`2 telemetryProperties, Dictionary`2 telemetryMetrics)
at SSC.Chatbot.QnABot`1.OnMessageActivityAsync(ITurnContext`1 turnContext, CancellationToken cancellationToken) in D:\a\1\s\Bots\QnABot.cs:line 121
at Microsoft.Bot.Builder.ActivityHandler.OnTurnAsync(ITurnContext turnContext, CancellationToken cancellationToken)
at SSC.Chatbot.QnABot`1.OnTurnAsync(ITurnContext turnContext, CancellationToken cancellationToken) in D:\a\1\s\Bots\QnABot.cs:line 97
at Microsoft.Bot.Builder.TelemetryLoggerMiddleware.OnTurnAsync(ITurnContext context, NextDelegate nextTurn, CancellationToken cancellationToken)
at Microsoft.Bot.Builder.Integration.ApplicationInsights.Core.TelemetryInitializerMiddleware.OnTurnAsync(ITurnContext context, NextDelegate nextTurn, CancellationToken cancellationToken)
at Microsoft.Bot.Builder.BotFrameworkAdapter.TenantIdWorkaroundForTeamsMiddleware.OnTurnAsync(ITurnContext turnContext, NextDelegate next, CancellationToken cancellationToken)
at Microsoft.Bot.Builder.MiddlewareSet.ReceiveActivityWithStatusAsync(ITurnContext turnContext, BotCallbackHandler callback, CancellationToken cancellationToken)
at Microsoft.Bot.Builder.BotAdapter.RunPipelineAsync(ITurnContext turnContext, BotCallbackHandler callback, CancellationToken cancellationToken)

已在Azure门户中确认报错路径下的模型文件真实存在，相关凭证截图：

• 升级Azure App Service定价层：多语言Unicoder模型体积约1.8GB，加载时需额外预留2~3GB运行内存，免费层/F1/B1层可用内存不足以支撑加载，英文模型体积更小所以可正常运行，建议至少升级到B2及以上配置。
• 切换为64位运行时：进入Azure门户→App Service配置→常规设置，将平台设置为64位，关闭32位应用开关，多语言ONNX模型仅支持64位运行时加载。
• 调整模型加载逻辑：改为首次调用时异步懒加载模型，不要在应用启动阶段同步加载，避免启动时内存占用过高触发Azure进程回收机制。
• 检查配套文件完整性：确认模型对应vocab词汇表文件也同步上传到模型同目录下，不要仅上传.onnx单个模型文件。
• 替代部署方案：如果业务必须使用多语言模型且不想升级App Service配置，可将Orchestrator服务托管到Azure Functions弹性Premium计划（EP2及以上）或者Azure容器实例中运行，内存限制更宽松。

内容的提问来源于stack exchange，提问作者nephinj