# \#pytorch

**URL:** https://community.ultralytics.com/tag/pytorch/111.md

[Latest](https://community.ultralytics.com/latest.md) · [Categories](https://community.ultralytics.com/categories.md) · [Tags](https://community.ultralytics.com/tags.md)

---

## [GPU memory leak](https://community.ultralytics.com/t/gpu-memory-leak/967)

<div class="topic-metadata">

**Author:** [@MaestroV](https://community.ultralytics.com/u/MaestroV)\
**Replies:** 20\
**Last updated:** [September 9, 2025, 12:44pm UTC](https://community.ultralytics.com/t/gpu-memory-leak/967 "2025-09-09T12:44:13Z")

</div>

python NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 NVIDIA GeForce RTX 4060 ultralytics==8.3.107 ultralytics-thop==2.0.14 ubuntu 24.04 torch==2.6.0 Hello. Please help me. Ye…

---

## [YOLO to lighter versions conversion for CPU deployement](https://community.ultralytics.com/t/yolo-to-lighter-versions-conversion-for-cpu-deployement/1175)

<div class="topic-metadata">

**Author:** [@aacha](https://community.ultralytics.com/u/aacha)\
**Replies:** 1\
**Last updated:** [June 25, 2025, 12:50pm UTC](https://community.ultralytics.com/t/yolo-to-lighter-versions-conversion-for-cpu-deployement/1175 "2025-06-25T12:50:07Z")

</div>

My current object detection best.pt which was based on yolo11s architecture is too lagging in cpu, but i have to deploy the model in CPU to process realtime footages. So should I try ONNX conversion or is there any bette…

---

## [Community Notice: :pytorch: Critical CVE](https://community.ultralytics.com/t/community-notice-critical-cve/1024)

<div class="topic-metadata">

**Author:** [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\
**Replies:** 0\
**Last updated:** [April 29, 2025, 1:47pm UTC](https://community.ultralytics.com/t/community-notice-critical-cve/1024 "2025-04-29T13:47:43Z")

</div>

CVE-2025-32434 in PyTorch A critical vulnerability (CVSS 9.3) :skull: has been identified in PyTorch versions \< 2.6.0. Exploiting this issue via torch.load with weights\_only=True could allow remote code execution (RCE) d…

---

## [Expecting torch and torchvision for JP6.1](https://community.ultralytics.com/t/expecting-torch-and-torchvision-for-jp6-1/376)

<div class="topic-metadata">

**Author:** [@jiapei100](https://community.ultralytics.com/u/jiapei100)\
**Replies:** 9\
**Last updated:** [December 20, 2024, 5:44pm UTC](https://community.ultralytics.com/t/expecting-torch-and-torchvision-for-jp6-1/376 "2024-12-20T17:44:42Z")

</div>

Hi, all: I noticed https://docs.ultralytics.com/guides/nvidia-jetson/#install-ultralytics-package, torch and torchvision now only support JP6.0. However, JP6.1 is already released, please see https://forums.developer.nv…

---

## [\[PSA\] Issues observed with PyTorch 2.4.0 + Ultralytics](https://community.ultralytics.com/t/psa-issues-observed-with-pytorch-2-4-0-ultralytics/139)

<div class="topic-metadata">

**Author:** [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\
**Replies:** 1\
**Last updated:** [July 26, 2024, 3:18pm UTC](https://community.ultralytics.com/t/psa-issues-observed-with-pytorch-2-4-0-ultralytics/139 "2024-07-26T15:18:42Z")

</div>

What going on? :pytorch: PyTorch 2.4.0 was released for general availability earlier this week. Ultralytics has observed some odd behavior, specifically on Windows with this new PyTorch version. Conditions for issue Wi…

---

## [\[PyTorch\] :pytorch: New version incoming!](https://community.ultralytics.com/t/pytorch-new-version-incoming/128)

<div class="topic-metadata">

**Author:** [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\
**Replies:** 1\
**Last updated:** [July 25, 2024, 12:04pm UTC](https://community.ultralytics.com/t/pytorch-new-version-incoming/128 "2024-07-25T12:04:11Z")

</div>

:pytorch: Release day for 2.4.0 will be 2024-07-24 :eyes: so be sure to check your dependencies and roll back if you experience any issues with PyTorch 2.4.0 and Ultralytics.