| |
| """ASGI serving app of frnet-p150 on one Tenstorrent Blackhole p150: the HTTP contract of the Autoware |
| collection (vendored ``ttaw.server.app``, BUNDLE_CONVENTIONS.md section 7) bound to :class:`FRNet`. |
| |
| Served by tt-model-manager as ``kind: tt-dit-server``:: |
| |
| python -m uvicorn --host 0.0.0.0 --port <p> --lifespan on tt_frnet.server.app:app |
| |
| Routes: ``GET /``, ``/health`` and ``/v1/health`` (always 200: ``ok`` / ``starting`` / ``error``), ``/info``, |
| ``/v1/models`` (stub), ``POST /predict``; errors 400 / 422 / 503 / 500 (SERVING.md section 3). Everything that |
| touches the device happens in the lifespan: weights -> device (ETH dispatch, 12x10) -> graph -> trace capture of |
| every warm-up variant, so uvicorn's ``Application startup complete`` (the line ``tt-model serve`` waits for) means |
| warm; SIGTERM (``tt-model stop``, 120 s) closes the model under the lock. ``/predict`` calls the Python API, so it |
| returns exactly what ``model(...)`` returns. Importing this module has no side effects beyond importing fastapi and |
| pydantic (the image's ``verify:`` imports it without a device); the environment is read in the lifespan only. |
| |
| Model-specific request fields (e.g. PointPainting ``rois``): subclass ``PredictRequest``, pass ``request_model=`` and |
| ``decode_extra=`` (which adds the decoded field to the call kwargs) to :class:`ServerSpec`, and list the keyword in |
| ``EXTRA_INPUTS`` of the model class. Host tests swap the model before starting the app: |
| ``app.state.ttaw.model_factory = Stub``; ``app.state.ttaw.predict(request)`` is the route handler itself. |
| """ |
| from pathlib import Path |
|
|
| from .. import __version__ |
| from ..api import FRNet |
| from ..ttaw.server.app import PredictRequest, ServerSpec, create_app, parse_mesh_shape |
|
|
| __all__ = ["SPEC", "app", "PredictRequest", "parse_mesh_shape"] |
|
|
| SPEC = ServerSpec( |
| model_name=FRNet.MODEL_NAME, |
| env_prefix=FRNet.ENV_PREFIX, |
| model_cls=FRNet, |
| task="LiDAR 3D semantic segmentation", |
| default_weights=FRNet.DEFAULT_REPO, |
| owner="changh95", |
| io="one LiDAR sweep in the sensor frame (x, y, z, raw 0-255 intensity) in, a class id and probability for every point (27 T4 classes; Autoware's interpolated points included) out", |
| autoware={"package": "autoware_lidar_frnet", |
| "path": "perception/autoware_lidar_frnet", |
| "autoware_universe": "9ceaccf026c31ffc5319bc9eeb4bd7bede0af3fd"}, |
| source={"repo": "https://huggingface.co/changh95/frnet-p150", "license": "Apache-2.0"}, |
| calib_dir=Path(__file__).resolve().parents[1] / "calib", |
| version=__version__, |
| description="FRNet (Autoware lidar_frnet) on one Tenstorrent Blackhole p150. " |
| "Not an OpenAI-compatible API.", |
| ) |
|
|
| app = create_app(SPEC) |
|
|
