Starstruk Logo MarkStarstruk

v1.1.2

alibaba/MNNv1.1.2Mar 20, 2026by PawelPeczek-Roboflow

AI Summary

This release adds GLM-OCR support, Redis-based quota management, and various performance optimizations like CUDA graphs and cache watchdogs.

Key Highlights

  • Added GLM-OCR support.
  • Added Redis-based workspace stream quota for WebRTC sessions.
  • Added option to use CUDA graphs with TRT for RF-DETR.
  • Added Semantic Segmentation Model workflow block.

New Features

  • GLM-OCR support
  • Redis-based quota management
  • CUDA graphs for TRT
  • Cache watchdog implementation
  • Semantic segmentation workflow block
  • S3 Sink workflow block

Full Release Notes

## What's Changed
* Add ability to override pre-processing per model forward-pass in `inference-models` by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2120
* Fix video billing for rtsp by @digaobarbosa in https://github.com/roboflow/inference/pull/2117
* Add option to use CUDA graphs with TRT for RF-DETR Object Detection in `inference_models` by @mkaic in https://github.com/roboflow/inference/pull/1938
* feat: Add Redis-based workspace stream quota for WebRTC sessions by @rafel-roboflow in https://github.com/roboflow/inference/pull/2025
* Add implementation for inference-models cache watchdog in old inference by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2122
* Create Semantic Segmentation Model workflow block by @leeclemnet in https://github.com/roboflow/inference/pull/2028
* Fix SAM3 visual segment concurrency race (DATAMAN-183) by @digaobarbosa in https://github.com/roboflow/inference/pull/2124
* Fix workflow spec fetch to fall back to file cache on timeout by @alexnorell in https://github.com/roboflow/inference/pull/2127
* GLM-OCR support by @Erol444 in https://github.com/roboflow/inference/pull/2126
* Add S3 Sink workflow block by @Jonathan-Roboflow in https://github.com/roboflow/inference/pull/2129
* Add detections area property extraction and UQL property_name_options by @dkosowski87 in https://github.com/roboflow/inference/pull/2132
* added gpt 5.4 mini/nano models to workflow blocks by @Erol444 in https://github.com/roboflow/inference/pull/2125
* Add dkosowski87 to other repo elements as codeowner by @dkosowski87 in https://github.com/roboflow/inference/pull/2135
* added reference overview page, updated inference py package about page by @Erol444 in https://github.com/roboflow/inference/pull/2119
* Feature/extend glm ocr by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2133
* GLM-OCR docs by @Erol444 in https://github.com/roboflow/inference/pull/2134
* Revert change with making inference models default backend by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2136

## New Contributors
* @Jonathan-Roboflow made their first contribution in https://github.com/roboflow/inference/pull/2129

**Full Changelog**: https://github.com/roboflow/inference/compare/v1.1.1...v1.1.2