v1.1.0

# ℹ️ About `1.1.0` release
This `inference` release brings important changes to the ecosystem:
* We have deprecated Python 3.9 which reached EOL
* We **have not** made `inference-models` the default backend for running predictions - this change is postponed until version `1.2.0`.

# 🚀 Added

## 🧠 Qwen3.5
Thanks to [@Matvezy](https://github.com/Matvezy), `inference` now supports the new Qwen3.5 model.

Qwen3.5 is Alibaba's latest open-source model family (released Feb 2026), ranging from 0.8B to 397B parameters. The headline features are native multimodal (text + vision) support. `inference` and Workflows support small 0.8B parameters version.

**Model is available only with `inference-models` backend** - released in `inference-models 0.20.0`

## 🪄 GPT-5.4 support
Thanks to [@Erol444](https://github.com/Erol444), the LLM Workflows block now supports GPT-5.4, keeping inference current with the latest OpenAI model lineup.

## ⚙️ Selectable inference backend for batch processing
Following up on `inferemce 1.0.0` release, Roboflow clients can now select which inference backend is used for batch processing — giving more fine-grained control when mixing legacy and new engine workloads.

Using `inference-cli`, one can specify which models backend will be selected `inference-models` or `old-inference`.
```bash
inference rf-cloud batch-processing process-images-with-workflow \
    --workflow-id <your-workflow> \
    --batch-id <your-batch> \
    --api-key<your-api-key> \
    --inference-backend inference-models
# or - for videos
inference rf-cloud batch-processing process-videos-with-workflow \
    --workflow-id <your-workflow> \
    --batch-id <your-batch> \
    --api-key<your-api-key> \
    --inference-backend inference-models
```

The same can be configured in Roboflow App and via HTTP integration - check out [swagger](https://inference.roboflow.com/workflows/batch_processing/api_reference/#batch-processing-api)

> [!CAUTION]
> Currently, the default backend is `old-inference`, but that will change in the nearest future - Roboflow clients should verify new backend and make necessary adjustments in their integrations if they want to still use `old-inference` backend.

# 🦺 Maintanence

## 🐍 Drop of Python 3.9 and upgrade to `transformers>=5`

We've ported all public builds to work with versions of Python newer than 3.9, which was slowing us down when it comes to onboarding new features. Thanks to deprecation, we could migrate to `transformers>=5` and enable new model - Qwen 3.5.

## Other changes
* Fix theme build by @Erol444 in https://github.com/roboflow/inference/pull/2093
* fix docs.yml to correctly build css by @Erol444 in https://github.com/roboflow/inference/pull/2095
* fix: pinned models no longer block LRU eviction by @hansent in https://github.com/roboflow/inference/pull/2091
* Add support for pushing back to client HTTP 402 errors by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2099
* Add env flag to globally disable selected inference-models backends by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2096
* Added RF-DETR by @Erol444 in https://github.com/roboflow/inference/pull/2098
* Qwen3 5 improvements by @Matvezy in https://github.com/roboflow/inference/pull/2101
* Fix OpenCV ffmpeg/gstreamer support in JP51 core image by @alexnorell in https://github.com/roboflow/inference/pull/2100
* Release/1.1.0 by @PawelPeczek-Roboflow in https://github.com/roboflow/inference/pull/2102


**Full Changelog**: https://github.com/roboflow/inference/compare/v1.0.5...v1.1.0