v1.7.3

# 🚀 Added

## 🍎 RF-DETR finally feels at home on a Mac

Until now, RF-DETR on a Mac ran *slower* on Core ML than on plain CPU: ONNX Runtime picked the legacy Core ML format, which can't do LayerNorm or GELU, and chopped the graph into ~100 pieces. Two fixes. ONNX models now ask for an ML Program, so RF-DETR Nano goes from 72 ms to 16 ms end to end. And when a model has a native Core ML package (Roboflow Train has built one for every RF-DETR since July 2025), `AutoModel` runs it directly: Nano 10 ms, Large 19 ms, versus 49 / 200 ms on CPU, with COCO AP within 0.01. Author's numbers, M4 Max. Oversized models are now rejected *before* the expensive compile, not after (@yeldarby, https://github.com/roboflow/inference/pull/3082, https://github.com/roboflow/inference/pull/3085; @dkosowski87, https://github.com/roboflow/inference/pull/3100).

## 🧬 Your classifier already knows what "normal" looks like

New `roboflow_core/embedding_model@v1` pulls the feature vector (or raw logits) out of a classifier you already trained: ResNet, ViT or DINOv3, plus the pretrained ResNet aliases. No retraining. Plug the output straight into Cosine Similarity for novelty detection or "find me more like this". Also available as `POST /infer/embeddings` and in the SDK (@yeldarby, https://github.com/roboflow/inference/pull/3095).

## 🧠 Two more brains

Claude Sonnet 5.5 in `anthropic_claude@v5` and GPT-6.1 Sol in `open_ai@v7`, with `low` to `max` reasoning effort (@SkalskiP  https://github.com/roboflow/inference/pull/3076, https://github.com/roboflow/inference/pull/3081).

# 🔧 Fixed

- **A long CLIP prompt is your problem now, not ours** — text past CLIP's 77 tokens returns 400 instead of 500, on both model backends and in the CLIP Workflow blocks (@PawelPeczek-Roboflow, https://github.com/roboflow/inference/pull/3084).
- **RF-DETR trusts the model over the paperwork** — some packages said 640×640 while the ONNX file wanted 384×384, so every call failed. The loader now believes the weights (@yeldarby, https://github.com/roboflow/inference/pull/3089).
- **Your webcam does 30 FPS again** — `fourcc` is applied before `fps`, so a Logitech C920 at 1080p switches to MJPG instead of crawling at 5 FPS in YUYV (@ColePBryan, https://github.com/roboflow/inference/pull/3105).
- **RF-DETR works on a read-only Jetson 6.2 container** — Triton's kernel cache now goes to `/tmp`, as on JetPack 7.2 (@JeremyGracey-AI, https://github.com/roboflow/inference/pull/3072).
- **The community forum link goes to the community forum** (@pratikgx, https://github.com/roboflow/inference/pull/3096).

# ⚙️ Execution Engine `v1.16.1`

`1.16.0` → `1.16.1`: dependency preloading tells classification, feature-vector and logits uses of the same model apart. Existing workflows need no migration. Details in [`workflows/CHANGELOG.md`](https://github.com/roboflow/inference/blob/v1.7.3/workflows/CHANGELOG.md).

# 🚧 Maintenance

- **Versions** — `inference` `1.7.3`, `inference-models` `0.39.1`, `roboflow-workflows` `0.2.4`, `streamvision` `0.1.0` (@grzegorz-roboflow, https://github.com/roboflow/inference/pull/3114).
- **supervision 0.30.6** — results stay the same, with two small exceptions: Time in Zone can flip for an anchor within 1 px of a zone edge, and Detections Stitch with NMM is slower on large frames in NumPy mode (@grzegorz-roboflow, https://github.com/roboflow/inference/pull/3079).
- **Security refresh** — Python and npm dependency patches (https://github.com/roboflow/inference/pull/3111, https://github.com/roboflow/inference/pull/3108).
- **CI** — automated PR review runs on Claude Opus 5.5 (https://github.com/roboflow/inference/pull/3107), the fast-track lane dropped a dormant suite (https://github.com/roboflow/inference/pull/3077), integration tests cache their assets (@ecarrara, https://github.com/roboflow/inference/pull/3104), linters are happy (https://github.com/roboflow/inference/pull/3070).
- **Docs site analytics** move off Segment (@franklin-robo, https://github.com/roboflow/inference/pull/3071).

## New Contributors
* @franklin-robo made their first contribution in https://github.com/roboflow/inference/pull/3071
* @pratikgx made their first contribution in https://github.com/roboflow/inference/pull/3096
* @JeremyGracey-AI made their first contribution in https://github.com/roboflow/inference/pull/3072
* @ColePBryan made their first contribution in https://github.com/roboflow/inference/pull/3105

**Full Changelog**: https://github.com/roboflow/inference/compare/v1.7.2...v1.7.3