furiosa.server.api.grpc.generated package

Submodules

furiosa.server.api.grpc.generated.model_repository_pb2 module

Generated protocol buffer code.

furiosa.server.api.grpc.generated.model_repository_pb2_grpc module

Client and server classes corresponding to protobuf-defined services.

class furiosa.server.api.grpc.generated.model_repository_pb2_grpc.ModelRepositoryService

Bases: object

Missing associated documentation comment in .proto file.

static RepositoryIndex(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static RepositoryModelLoad(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static RepositoryModelUnload(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

class furiosa.server.api.grpc.generated.model_repository_pb2_grpc.ModelRepositoryServiceServicer

Bases: object

Missing associated documentation comment in .proto file.

RepositoryIndex(request, context)

Get the index of model repository contents.

RepositoryModelLoad(request, context)

Load or reload a model from a repository.

RepositoryModelUnload(request, context)

Unload a model.

class furiosa.server.api.grpc.generated.model_repository_pb2_grpc.ModelRepositoryServiceStub(channel)

Bases: object

Missing associated documentation comment in .proto file.

furiosa.server.api.grpc.generated.model_repository_pb2_grpc.add_ModelRepositoryServiceServicer_to_server(servicer, server)

furiosa.server.api.grpc.generated.predict_pb2 module

Generated protocol buffer code.

furiosa.server.api.grpc.generated.predict_pb2_grpc module

Client and server classes corresponding to protobuf-defined services.

class furiosa.server.api.grpc.generated.predict_pb2_grpc.GRPCInferenceService

Bases: object

Inference Server GRPC endpoints.

static ModelInfer(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static ModelMetadata(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static ModelReady(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static ServerLive(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static ServerMetadata(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

static ServerReady(request, target, options=(), channel_credentials=None, call_credentials=None, insecure=False, compression=None, wait_for_ready=None, timeout=None, metadata=None)

class furiosa.server.api.grpc.generated.predict_pb2_grpc.GRPCInferenceServiceServicer

Bases: object

Inference Server GRPC endpoints.

ModelInfer(request, context)

The ModelInfer API performs inference using the specified model. Errors are indicated by the google.rpc.Status returned for the request. The OK code indicates success and other codes indicate failure.

ModelMetadata(request, context)

The per-model metadata API provides information about a model. Errors are indicated by the google.rpc.Status returned for the request. The OK code indicates success and other codes indicate failure.

ModelReady(request, context)

The ModelReady API indicates if a specific model is ready for inferencing.

ServerLive(request, context)

The ServerLive API indicates if the inference server is able to receive and respond to metadata and inference requests.

ServerMetadata(request, context)

The ServerMetadata API provides information about the server. Errors are indicated by the google.rpc.Status returned for the request. The OK code indicates success and other codes indicate failure.

ServerReady(request, context)

The ServerReady API indicates if the server is ready for inferencing.

class furiosa.server.api.grpc.generated.predict_pb2_grpc.GRPCInferenceServiceStub(channel)

Bases: object

Inference Server GRPC endpoints.

furiosa.server.api.grpc.generated.predict_pb2_grpc.add_GRPCInferenceServiceServicer_to_server(servicer, server)

Module contents