Pipeline Builder [Alpha]
The Pipeline Builder is the Pythonic API for building ML inference pipelines on the Axelera Metis AIPU. Where YAML pipelines give you optimized GStreamer throughput for production deployment, the Pipeline Builder gives you composable Python operators for custom inter-stage logic, rapid prototyping, and workflows that go beyond standard detect-and-track patterns.
important
Alpha The Pipeline Builder API is an early alpha release and currently does not run at its target performance. We do not yet advise to use it for any workloads where performance is critical, such as benchmarks or production workloads. Pipeline Builder will reach top performance and become the recommended API for running models on Axelera hardware in the next Voyager SDK release(s).
Start here
- Quickstart — your first pipeline in under a minute
- Model Compilation — compile your model to
.axm(Ultralytics, ONNX, or PyTorch) - Pipeline Overview — full reference with examples for every task type
Operator reference
- Transforms — image preprocessing (resize, letterbox, normalize, color convert)
- Postprocess — decode raw model output, NMS, coordinate transform, filter
- Results — convert arrays to typed objects (DetectedObject, PoseObject, etc.)
- Inference — model loading (
op.load,op.onnx_model) - Tracker — multi-object tracking (ByteTrack, OC-SORT, SORT, TrackTrack)
- Combinators — pipeline composition (
op.seq,op.par,op.for_each)
Type reference
- Types — BBox, DetectedObject, PoseObject, SegmentedObject, TrackedObject, Classification