"""Apollo training plugin for vLLM.

Enables continuous fine-tuning alongside live inference by:
1. Exporting CUDA IPC handles for weight sharing (export_hook)
2. Adding /train endpoint to vLLM's HTTP server (train_router)
3. Block-level checkpoint sync to safetensors files

Install: pip install -e /path/to/training
Then vLLM auto-loads via entry point.
"""

from .export_hook import _patch_model_runner
from .train_router import _patch_api_server


def register():
    """Called by vLLM's plugin loader on startup."""
    _patch_model_runner()
    _patch_api_server()