NVIDIA · Python DLA Runtime

cuda.bindings.cudla (cuDLA Python API)

NVIDIA has added cuda.bindings.cudla, a Cython-generated Python layer over the cuDLA C++ API, introduced in cuda-bindings 13.3.0 as part of the CUDA Python project. It exposes thirteen functions, nine data types and eight enums for hybrid-mode workflows, where CUDA streams coordinate DLA inference with GPU preprocessing and postprocessing on Jetson AGX Orin. The post walks through a nine-step image classification lifecycle, and the API is stated to be identical on NVIDIA RTX Spark Windows laptops. Standalone mode is not supported in this release.

Open the source ↗

Similar Developer Tools releases

  • llama.cpp v1.0.0

    ggml-org and Hugging Face · Local inference library · Week 47, 2026

  • MACaQ

    Huawei CSL (huawei-csl) · Model quantisation toolkit · Week 47, 2026

  • Needle 3

    Cactus Compute · Tiny Device Model · Week 39, 2026

  • edge0

    Edge0-AI · Streaming MoE Inference · Week 37, 2026

  • Magnitude

    magnitudedev · Local Model Server · Week 36, 2026

  • SwarmLLM

    SwarmLLM · Peer-to-Peer Inference · Week 36, 2026

More from NVIDIA

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.