modeld: retain SNPE and thneed drive model support (#530)

* modeld: Retain pre-20hz drive model support * Method not available anymore on OP * some fixes * Revert "Long planner get accel: new function args (#34288)" * Revert "Fix low-speed allow_throttle behavior in long planner (#33894)" * Revert "long planner: allow throttle reflects usage (#33792)" * Revert "Gate acceleration on model gas press predictions (#33643)" * Reapply "Gate acceleration on model gas press predictions (#33643)" This reverts commit 76b08e37cb8eb94266ad9f6fed80db227e7c3428. * Reapply "long planner: allow throttle reflects usage (#33792)" This reverts commit c75244ca4e9c48084b0205b7c871e1a4e0f4e693. * Reapply "Fix low-speed allow_throttle behavior in long planner (#33894)" This reverts commit b2b7d21b7b685a2785d1beede3d223f0bb954807. * Reapply "Long planner get accel: new function args (#34288)" This reverts commit 74dca2fccf4da59cc8ac62ba9c0ad10ba3fc264b. * don't need * retain snpe * wrong * they're symlinks * remove * put back into VCS * add back * don't include built * Refactor model runner retrieval with caching support Added caching for active model runner type via `ModelRunnerTypeCache` to enhance performance and avoid redundant checks. Introduced a `force_check` flag to bypass the cache when necessary. Updated related code to handle cache clearing during onroad transitions. * Update model runner determination logic with caching fix Enhances `get_active_model_runner` to utilize caching more effectively by ensuring type consistency and updating cache only when necessary. Also updates `is_snpe_model` to pass the `started` state to the runner determination function, improving behavior for dynamic checks. * default to none * enable in next PR * more --------- Co-authored-by: DevTekVE <devtekve@gmail.com>
2026-09-12 11:13:46 +08:00 · 2025-01-10 08:56:10 -05:00
parent d5f5887830
commit 56aa07844a
109 changed files with 9475 additions and 3 deletions
@@ -0,0 +1,92 @@
+//=============================================================================
+//
+//  Copyright (c) 2015-2016 Qualcomm Technologies, Inc.
+//  All Rights Reserved.
+//  Confidential and Proprietary - Qualcomm Technologies, Inc.
+//
+//=============================================================================
+
+#ifndef _ITENSOR_FACTORY_HPP
+#define _ITENSOR_FACTORY_HPP
+
+#include "ITensor.hpp"
+#include "TensorShape.hpp"
+#include "ZdlExportDefine.hpp"
+#include <istream>
+
+namespace zdl {
+    namespace DlSystem
+    {
+        class ITensor;
+        class TensorShape;
+    }
+}
+
+namespace zdl { namespace DlSystem
+{
+
+/** @addtogroup c_plus_plus_apis C++
+@{ */
+
+/**
+ * Factory interface class to create ITensor objects.
+ */
+class ZDL_EXPORT ITensorFactory
+{
+public:
+   virtual ~ITensorFactory() = default;
+
+   /**
+    * Creates a new ITensor with uninitialized data. 
+    *  
+    * The strides for the tensor will match the tensor dimensions 
+    * (i.e., the tensor data is contiguous in memory).
+    *  
+    * @param[in] shape The dimensions for the tensor in which the last
+    * element of the vector represents the fastest varying
+    * dimension and the zeroth element represents the slowest
+    * varying, etc.
+    * 
+    * @return A pointer to the created tensor or nullptr if creating failed.
+    */
+   virtual std::unique_ptr<ITensor>
+      createTensor(const TensorShape &shape) noexcept = 0;
+
+   /**
+    * Creates a new ITensor by loading it from a file.
+    *  
+    * @param[in] input The input stream from which to read the tensor 
+    *                  data.
+    *  
+    * @return A pointer to the created tensor or nullptr if creating failed.
+    *
+    */
+   virtual std::unique_ptr<ITensor> createTensor(std::istream &input) noexcept = 0;
+
+   /**
+    * Create a new ITensor with specific data.
+    * (i.e. the tensor data is contiguous in memory). This tensor is
+    * primarily used to create a tensor where tensor size can't be
+    * computed directly from dimension. One such example is
+    * NV21-formatted image, or any YUV formatted image
+    *
+    * @param[in] shape The dimensions for the tensor in which the last
+    * element of the vector represents the fastest varying
+    * dimension and the zeroth element represents the slowest
+    * varying, etc.
+    *
+    * @param[in] data The actual data with which the Tensor object is filled.
+    *
+    * @param[in] dataSize The size of data
+    *
+    * @return A pointer to the created tensor
+    */
+   virtual std::unique_ptr<ITensor>
+      createTensor(const TensorShape &shape, const unsigned char *data, size_t dataSize) noexcept = 0;
+};
+
+}}
+
+/** @} */ /* end_addtogroup c_plus_plus_apis C++ */
+
+#endif