server

Documentation

Overview

Copyright 2021 IBM Corporation

Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.

Copyright 2021 IBM Corporation

Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.

Index

• type AdapterConfiguration
  • func GetAdapterConfigurationFromEnv(log logr.Logger) (*AdapterConfiguration, error)
• type MLServerAdapterServer
  • func NewMLServerAdapterServer(runtimePort int, config *AdapterConfiguration, log logr.Logger) *MLServerAdapterServer
  • func (s *MLServerAdapterServer) LoadModel(ctx context.Context, req *mmesh.LoadModelRequest) (*mmesh.LoadModelResponse, error)
  • func (s *MLServerAdapterServer) RuntimeStatus(ctx context.Context, req *mmesh.RuntimeStatusRequest) (*mmesh.RuntimeStatusResponse, error)
  • func (s *MLServerAdapterServer) UnloadModel(ctx context.Context, req *mmesh.UnloadModelRequest) (*mmesh.UnloadModelResponse, error)

Types

type AdapterConfiguration

type AdapterConfiguration struct {
	Port                         int
	MLServerPort                 int
	MLServerContainerMemReqBytes int
	MLServerMemBufferBytes       int
	CapacityInBytes              int
	MaxLoadingConcurrency        int
	ModelLoadingTimeoutMS        int
	DefaultModelSizeInBytes      int
	ModelSizeMultiplier          float64
	RuntimeVersion               string
	LimitModelConcurrency        int // 0 means no limit (default)
	RootModelDir                 string
	UseEmbeddedPuller            bool
}

func GetAdapterConfigurationFromEnv

func GetAdapterConfigurationFromEnv(log logr.Logger) (*AdapterConfiguration, error)

type MLServerAdapterServer

type MLServerAdapterServer struct {
	Client        mlserver.GRPCInferenceServiceClient
	Conn          *grpc.ClientConn
	Puller        *puller.Puller
	AdapterConfig *AdapterConfiguration
	Log           logr.Logger

	// embed generated Unimplemented type for forward-compatibility for gRPC
	mmesh.UnimplementedModelRuntimeServer
}

func NewMLServerAdapterServer

func NewMLServerAdapterServer(runtimePort int, config *AdapterConfiguration, log logr.Logger) *MLServerAdapterServer

func (*MLServerAdapterServer) LoadModel

func (s *MLServerAdapterServer) LoadModel(ctx context.Context, req *mmesh.LoadModelRequest) (*mmesh.LoadModelResponse, error)

func (*MLServerAdapterServer) RuntimeStatus

func (s *MLServerAdapterServer) RuntimeStatus(ctx context.Context, req *mmesh.RuntimeStatusRequest) (*mmesh.RuntimeStatusResponse, error)

func (*MLServerAdapterServer) UnloadModel

func (s *MLServerAdapterServer) UnloadModel(ctx context.Context, req *mmesh.UnloadModelRequest) (*mmesh.UnloadModelResponse, error)