Lakshantha Dissanayake 94fac39036
ultralytics 8.4.32 Expand Axelera exportable models and tasks (#23844)
Signed-off-by: Lakshantha Dissanayake <lakshantha@ultralytics.com>
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Jing Qiu <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Tam Robb <129945934+tamrobb@users.noreply.github.com>
Co-authored-by: Francesco Mattioli <francesco.mttl@gmail.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Onuralp SEZER <onuralp@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2026-03-30 18:09:38 +02:00

899 B

description keywords
Axelera export utilities for converting PyTorch models to Axelera format for deployment on Metis AI processors. Supports INT8 quantization and optimized inference for computer vision workloads on Axelera hardware. Ultralytics, Axelera, model export, PyTorch to Axelera, Metis AI processor, INT8 quantization, computer vision, AI inference, edge AI, hardware acceleration

Reference for ultralytics/utils/export/axelera.py

!!! success "Improvements"

This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/axelera.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/axelera.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏

::: ultralytics.utils.export.axelera.torch2axelera