Skip to navigation

Release 1.0.0

Initial capabilities include:

  • Trajectory generation through native POST /v1/infer, OpenAI-compatible POST /v1/chat/completions, and the binary gRPC Predict API.
  • Visual question answering through POST /v1/vqa.
  • Automatic single-GPU profile selection with BF16, FP8, and W4A16 precision options on supported hardware.
  • Sample-data and payload-building tools for runnable 16-image trajectory and single-image VQA requests.
  • Per-trajectory rotations, kinematic comfort metrics, health checks, and Prometheus metrics.