# Qualcomm IM SDK release 1.7 Tab Qualcomm Linux Tab Ubuntu - *class* tabincludedirective - ## Release information Table : Software version | Software | Version | | --- | --- | | Yocto | Scarthgap 5.0.14 | | Kernel | 6.6.116 | Table : Release tag version | Release tag | Version | | --- | --- | | Firmware | r1.0\_00114.0 | | Manifest | qcom-6.6.116-QLI.1.7-Ver.1.1 | | Meta-qcom-extras | r1.0\_00115.0 | | Qualcomm IM SDK | qcom-6.6.116-QLI.1.7-Ver.1.1\_qim-product-sdk-2.2.1 | Table : Supported platforms and reference kits | SoC platforms | Reference kits | | --- | --- | | QCS6490 | | | QCS5430 | | | Qualcomm Dragonwing^TM^ IQ-9075 | | | Qualcomm Dragonwing^TM^ IQ-8275 | Qualcomm Dragonwing^TM^ IQ-8275 Beta Evaluation Kit (EVK) | ## Contents of the release The contents of the Qualcomm IM SDK release include: - Recipes for building the individual components: - Qualcomm^®^ Intelligent Multimedia SDK (IM SDK) - Lite Runtime (LiteRT) - Qualcomm^®^ Neural Processing SDK - Qualcomm^®^ AI Engine direct SDK To get started with the Qualcomm IM SDK, see [Qualcomm Intelligent Multimedia (IM SDK) Quick Start Guide](https://docs.qualcomm.com/doc/80-70023-51). ## New features The message broker plugins `qtimsgpub` and `qtimsgsub` now include support for the Kafka protocol. ## Sample applications The following new features are added in the AI sample applications: - Added support for the AI-HUB QAIRT models in object detection, segmentation, and classification applications. - Added support for generating a Python 3 virtual‑environment layer to enable running the TFLite models on native Python. - Updated the sample application to use the tensor parameter to specify the required output tensors in the `qtimlsnpe` plugin. For the complete list of sample applications supported in the Qualcomm IM SDK and instructions on how to run them, see [Sample applications](https://docs.qualcomm.com/doc/80-70023-50/topic/example-applications.html). ## Issues resolved The following issues are resolved in the Qualcomm IM SDK release: - Camera streams with lens distortion correction (LDC) or electronic image stabilization (EIS) enabled may experience stability issues due to an underlying issue within the camera userspace library. - The camera Perport feature (used for multicamera aggregation) may experience stability issues during back-to-back iterations due to an underlying issue within the camera userspace library. - Optimized docker creation time by using Yocto SDK instead of Yocto eSDK. - Concurrent streams with smart codec functionality encounter pipeline stalls at the end of the stream. The following issues related to AI-specific sample applications are resolved in the Qualcomm IM SDK release: - Resolved the FPS drop issue in the `gst-ai-daisychain-detection-classification` application. - Resolved an issue where the `gst-ai-event-encoder` application failed to operate with 720p input videos due to a caps mismatch, and where the output video became unplayable when an EOS event was received from the input file. ## Limitations The following are the known limitations in the Qualcomm IM SDK release: - Frame drops may be seen with detection models when using the deprecated `qtioverlay` plugin, particularly in cases with many detections. **Workaround**: Switch to `qtivoverlay` or `qtivcomposer`, which are the preferred plugins. - AI/ML parallel inference for 32 streams varies between 20–30 fps depending on the model and input stream, which is less than the expected 30 fps. - Frame drops are observed with the Qualcomm^®^ Neural Network plugin when running on GPU delegate. - Frame drops are observed in daisychain detection‑pose usecases when the pose detection load (people per frame × model inference time) exceeds the per‑frame time limit (33 ms for 30 fps). - Reverse playback is limited to video streams with a GOP length that fits within the buffer limitations of the video driver (<= 26). - For Dragonwing IQ-9075 and Dragonwing IQ-8275: > > > - Random corruption is observed at the beginning of playback for low-resolution (480p) NV12 UBWC-compressed streams. > - Stability issues are observed when running multibatch ML use cases. - The `waylandsink` plugin doesn’t support displaying windows at custom screen coordinates. - Support for python bindings of OpenCV isn’t enabled within the Qualcomm IM SDK docker container. - When using the `qtimlpostprocess` plugin for postprocessing, a display latency occurs after approximately 30 minutes of running ML use cases on a camera stream. - Use cases with files having dynamic resolution change (DRC) may fail. This issue occurs because the video driver allocates buffers that are only partially accessible to the GPU driver. - `qtiobjtracker` exhibits non‑linear execution‑time growth during extended runs, which can act as a performance bottleneck. - ROI isn’t being generated in daisychain detection‑classification use cases when using a USB camera source with the YUY2 format. - *class* tabincludedirective - ## Release information Table : Software version | Software | Version | | --- | --- | | Ubuntu | Noble 24.04 | | Kernel | 6.8.0 | Table : Supported platforms and reference kits | SoC platforms | Reference kits | | --- | --- | | QCS6490 | | | QCS5430 | | | Qualcomm Dragonwing^TM^ IQ-9075 | | | Qualcomm Dragonwing^TM^ IQ-8275 | Qualcomm Dragonwing^TM^ IQ-8275 Beta Evaluation Kit (EVK) | ## Contents of the release The contents of the Qualcomm IM SDK release include: - Recipes for building the individual components: - Qualcomm IM SDK - Lite Runtime (LiteRT) Note LiteRT was formerly known as TensorFlow Lite. - Qualcomm Neural Processing SDK - Qualcomm AI Engine direct SDK - Sample applications that demonstrate how to use the Qualcomm IM SDK to develop AI edge-based applications. To get started with the Qualcomm IM SDK, see [Qualcomm Intelligent Multimedia (IM SDK) Quick Start Guide](https://docs.qualcomm.com/bundle/publicresource/topics/80-70022-51/qmi-sdk-qsg-landing-page.html). ## New features - The message broker plugins `qtimsgpub` and `qtimsgsub` now include support for the Kafka protocol. - Supports Float32 for Freedreno. ## Sample applications The following new features are added in the AI sample applications: - Added support for the AI-HUB QAIRT models in object detection, segmentation, and classification applications. - Added support for generating a Python 3 virtual‑environment layer to enable running the TFLite models on native Python. - Updated the sample application to use the tensor parameter to specify the required output tensors in the `qtimlsnpe` plugin. For the complete list of sample applications supported in the Qualcomm IM SDK and instructions on how to run them, see [Sample applications](https://docs.qualcomm.com/doc/80-70023-50/topic/example-applications.html). ## Issues resolved The following issues are resolved in the Qualcomm IM SDK release: - Camera streams with lens distortion correction (LDC) or electronic image stabilization (EIS) enabled may experience stability issues due to an underlying issue within the camera userspace library. - The camera Perport feature (used for multicamera aggregation) may experience stability issues during back-to-back iterations due to an underlying issue within the camera userspace library. - Concurrent streams with smart codec functionality encounter pipeline stalls at the end of the stream. The following issues related to AI-specific sample applications are resolved in the Qualcomm IM SDK release: - Resolved the FPS drop issue in the `gst-ai-daisychain-detection-classification` application. - Resolved an issue where the `gst-ai-event-encoder` application failed to operate with 720p input videos due to a caps mismatch, and where the output video became unplayable when an EOS event was received from the input file. ## Limitations The following are the known limitations in the Qualcomm IM SDK release: - An intermittent defect affects the sample applications and may cause preview‑case execution failures. The issue will be fixed in a future release. - Frame drops may be seen with detection models when using the deprecated `qtioverlay` plugin, particularly in cases with many detections. **Workaround**: Switch to `qtivoverlay` or `qtivcomposer`, which are the preferred plugins. - AI/ML parallel inference for 32 streams varies between 20–30 fps depending on the model and input stream, which is less than the expected 30 fps. - Frame drops are observed with the Qualcomm Neural Network plugin when running on GPU delegate. - Frame drops are observed in daisychain detection‑pose usecases when the pose detection load (people per frame × model inference time) exceeds the per‑frame time limit (33 ms for 30 fps). - Reverse playback is limited to video streams with a GOP length that fits within the buffer limitations of the video driver (<= 26). - For Dragonwing IQ-9075 and Dragonwing IQ-8275: > > > - Random corruption is observed at the beginning of playback for low-resolution (480p) NV12 UBWC-compressed streams. > - Stability issues are observed when running multibatch ML use cases. - The `waylandsink` plugin doesn’t support displaying windows at custom screen coordinates. - Support for python bindings of OpenCV isn’t enabled within the Qualcomm IM SDK docker container. - When using the `qtimlpostprocess` plugin for postprocessing, a display latency occurs after approximately 30 minutes of running ML use cases on a camera stream. - Use cases with files having dynamic resolution change (DRC) may fail. This issue occurs because the video driver allocates buffers that are only partially accessible to the GPU driver. - `qtiobjtracker` exhibits non‑linear execution‑time growth during extended runs, which can act as a performance bottleneck. - ROI isn’t being generated in daisychain detection‑classification use cases when using a USB camera source with the YUY2 format. ## Related documents - [Qualcomm Intelligent Multimedia SDK (IM SDK) Reference](https://docs.qualcomm.com/doc/80-70023-50/topic/qimsdk_landing_page.html) - [Qualcomm Intelligent Multimedia (IM SDK) Quick Start Guide](https://docs.qualcomm.com/doc/80-70023-51/topic/qmi-sdk-qsg-landing-page.html) - [Qualcomm Dragonwing RB3 Gen 2 Development Kit Guide](https://docs.qualcomm.com/doc/80-70023-251/topic/landing-page.html) - [Qualcomm Dragonwing IQ-9075 Evaluation Kit user guide – Linux](https://docs.qualcomm.com/doc/80-70023-261/topic/iq9-ug-landing-page.html) - [Qualcomm Linux Build Guide](https://docs.qualcomm.com/doc/80-70023-254/topic/build_landing_page.html) - [Migration Guide](https://docs.qualcomm.com/doc/80-70023-150/topic/introduction.html) Last Published: May 14, 2026 [Previous Topic Qualcomm IM SDK release 2.0 RC1](https://docs.qualcomm.com/bundle/publicresource/80-80022-52/topics/qim-sdk-release-2-0.md) [Next Topic Qualcomm IM SDK release 1.6](https://docs.qualcomm.com/bundle/publicresource/80-80022-52/topics/qim-sdk-release-1-6.md)