inference
inference is 🌟 Summary 🚀 Ultralytics Inference v0.0.39 makes CPU inference with FP16 ONNX models faster and simpler by letting ONNX Runtime handle FP16-to-FP32 conversion automatically, while also updating brow.... It is ranked #811 on the Dev Radar, in AI dev tools, first seen 7 days ago and shared in 1 post (1.6k views).
Release v0.0.39 - Speed up FP16 CPU inference and remove the ONNX FP16 rewriter (#446) · ultralytics/inference · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} ultralytics / inference Public Uh oh! There was an error while loading. Please reload this page . Notifications You must be signed in to change notification settings…
What people said about inference on X
Ultralytics Inference v0.0.39 is here with faster FP16 ONNX inference on CPU. ⚡ In the supplied Ultralytics YOLO26n benchmark, detection latency drops from 34.0 → 23.3 ms, with even bigger gains across other tasks: ✅ Segmentation: 47.3 → 31.0 ms ✅ Pose: 38.4 → 23.9 ms ✅ OBB: 70.2 → 43.5 ms ✅ Depth: 114.2 → 68.0 ms…
— @ultralytics, 7 days ago · 39 likes · see the post
Alternatives to inference
- muse.ai — New connectors are live today. Come build with us.
- classifier.dev — now outperforms jev and is free
- mimo-v2.6 RL — Streaming the run
- academy.dair.ai — Chat with Paper
- Union Alpha — Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level…
- cua — Draft #3943
inference in numbers
- Rank on the Dev Radar: #811 of 1578
- Shared in 1 post by 1 account: @ultralytics
- 1.6k views on those posts
- First seen 7 days ago, last shared 7 days ago
- Pricing seen by Jev: open source
- Market: AI dev tools
FAQ
What is inference?
🌟 Summary 🚀 Ultralytics Inference v0.0.39 makes CPU inference with FP16 ONNX models faster and simpler by letting ONNX Runtime handle FP16-to-FP32 conversion automatically, while also updating brow... It was first shared on X 7 days ago and is ranked #811 on the Dev Radar.
Is inference free?
It is open source.
Who shared inference?
1 account on X, including @ultralytics, in 1 post totalling 1.6k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.