v0.64.6

roboflow/inferencev0.64.6Jan 30, 2026by grzegorz-roboflow

AI Summary

This release expands the model library by adding large RF-DETRs, Seg-COCO models, and initial YOLO26 support with configurable API timeouts.

Key Highlights

  • Added large RF-DETRs and Seg-COCO models to inference_models
  • Added configurable RF API timeout for inference-cli command interacting with RF-cloud
  • Added YOLO26 to inference_models
  • Fixed failing YOLO26 GPU integration tests

New Features

  • Add configurable RF API timeout for inference-cli command interacting with RF-cloud
  • Add YOLO26 to inference_models

Full Release Notes

## What's Changed
* Add large rf-detrs and seg coco models to inference_models by @Matvezy in https://github.com/roboflow/inference/pull/1944
* Add configurable RF API timeout for inference-cli command interacting with RF-cloud by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/1950
* Allow sv.Detections.data properties in extract-property block by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1948
* CI for deploying custom python block modal app by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1945
* in modal.custom_python_block.deploy.yml use deployment modal tokens by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1953
* Address internals imported from Supervision by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1951
* Add YOLO26 to `inference_models` by @mkaic in https://github.com/roboflow/inference/pull/1943
* Fix failing yolo26 gpu integration tests by @mkaic in https://github.com/roboflow/inference/pull/1956
* Disable automatic deployment of modal webexec by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1954
* 0.64.6 by @grzegorz-roboflow in https://github.com/roboflow/inference/pull/1957


**Full Changelog**: https://github.com/roboflow/inference/compare/v0.64.5...v0.64.6