easydel.inference.vinference.api_server

easydel.inference.vinference.api_server#

class easydel.inference.vinference.api_server.EndpointConfig(path: 'str', handler: 'tp.Callable', methods: 'list[str]', summary: 'tp.Optional[str]' = None, tags: 'tp.Optional[list[str]]' = None)[source]#

Bases: object

handler: Callable#
methods: list[str]#
path: str#
summary: Optional[str] = None#
tags: Optional[list[str]] = None#
easydel.inference.vinference.api_server.create_error_response(status_code: HTTPStatus, message: str) → JSONResponse[source]#
class easydel.inference.vinference.api_server.vInferenceApiServer(inference_map: Union[Dict[str, Any], Any] = None, inference_init_call: Optional[Callable[[], Any]] = None, max_workers: int = 10)[source]#

Bases: object

available_inference()[source]#
async chat_completions(request: ChatCompletionRequest)[source]#
count_tokens(request: CountTokenRequest)[source]#
fire(host='0.0.0.0', port=11556, metrics_port: Optional[int] = None, log_level='debug')[source]#
liveness()[source]#
patch_endpoints()[source]#

Register all endpoints with the FastAPI app.

readiness()[source]#
Contents