From 276e3e3a57411b46da23861416e3a66896ae39f0 Mon Sep 17 00:00:00 2001 From: Chirag Shilwant Date: Fri, 12 Dec 2025 16:56:22 +0530 Subject: [PATCH 1/2] feat(linux): Switch from Neo-AI-DLR to TVM-RT * With [0], the ti-tidl-osrt has now dropped Neo-AI-DLR [1] & switched to TVM-RT. Hence, update the documentation to highlight the same. * Fixes d61076ac9c1d499d3178e38ef4a65866f0b02b44 * While at it, also update section headers as per [2] [0] - https://git.ti.com/cgit/edgeai/meta-edgeai/commit/recipes-tisdk/ti-tidl/ti-tidl-osrt.bb?h=scarthgap&id=1b88fbdf717da6f0c3ac1a6d7d4b23d2dff5f63d [1] - https://github.com/neo-ai/neo-ai-dlr [2] - https://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html#sections Signed-off-by: Chirag Shilwant --- source/linux/index_Edge_AI.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/source/linux/index_Edge_AI.rst b/source/linux/index_Edge_AI.rst index 2ecf656a4..bb603c99d 100644 --- a/source/linux/index_Edge_AI.rst +++ b/source/linux/index_Edge_AI.rst @@ -1,10 +1,10 @@ -******* +####### Edge AI -******* +####### The SDK provides software and tools to let the users effectively balance deep learning performance with system power and cost on Texas Instrument’s processors for edge AI applications. We offer a practical embedded inference solution for next-generation vehicles, smart cameras, edge AI boxes, and autonomous machines and robots. In addition to general purpose micro processors, AM62Ax has integrated micro controllers, DSP, and accelerators for neural network, image, vision, and multimedia processing. With a few simple steps one can run high performance computer vision and deep learning demos using a live camera and display. - The SDK also enables an interplay of multiple open-source components such as GStreamer, OpenVx, OpenCV and deep learning runtime such as TFLite, ONNX and Neo-AI DLR. The reference applications showcase perception based examples such as image classification, object detection and semantic segmentation in both Python and C++ variants. The SDK supports edit-build-debug cycles directly on the target and also on PC to cross compile and build the applications. + The SDK also enables an interplay of multiple open-source components such as GStreamer, OpenVx, OpenCV and deep learning runtime such as TFLite, ONNX and TVM-RT. The reference applications showcase perception based examples such as image classification, object detection and semantic segmentation in both Python and C++ variants. The SDK supports edit-build-debug cycles directly on the target and also on PC to cross compile and build the applications. .. ifconfig:: CONFIG_part_family in ('AM62AX_family') From ae25c19f55b4b0afb13f353a5a184ff2b897fda7 Mon Sep 17 00:00:00 2001 From: Chirag Shilwant Date: Mon, 15 Dec 2025 15:14:53 +0530 Subject: [PATCH 2/2] ci: vocabs: Add TFLite, ONNX & TVM to accept.txt In accepet.txt, add TFLite, ONNX & TVM as recognized words for Vale. Signed-off-by: Chirag Shilwant --- .github/styles/config/vocabularies/PSDK/accept.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.github/styles/config/vocabularies/PSDK/accept.txt b/.github/styles/config/vocabularies/PSDK/accept.txt index ed6d84d66..75e90b917 100644 --- a/.github/styles/config/vocabularies/PSDK/accept.txt +++ b/.github/styles/config/vocabularies/PSDK/accept.txt @@ -30,3 +30,6 @@ mmdebstrap bdebstrap fdisk umount +TFLite +ONNX +TVM