slot

Documentation

Overview

Package slot enforces modeld's single active local model invariant.

Index

• type Option
  • func WithBackend(backend string) Option
  • func WithOwner(owner string) Option
• type Service
  • func New(backend transport.Service, opts ...Option) *Service
  • func (s *Service) Describe(ctx context.Context, req transport.OpenSessionRequest) (transport.ModelInfo, error)
  • func (s *Service) Embed(ctx context.Context, req transport.EmbedRequest) (transport.EmbedResult, error)
  • func (s *Service) LoadModel(ctx context.Context, req transport.LoadModelRequest) (transport.ActiveModel, error)
  • func (s *Service) OpenSession(ctx context.Context, req transport.OpenSessionRequest) (transport.Session, error)
  • func (s *Service) Status(ctx context.Context) (transport.DaemonStatus, error)
  • func (s *Service) UnloadModel(ctx context.Context, req transport.UnloadModelRequest) error

Types

type Option

type Option func(*Service)

Option configures a slot Service.

func WithBackend

func WithBackend(backend string) Option

WithBackend records the backend mode for Status.

func WithOwner

func WithOwner(owner string) Option

WithOwner records the owner instance expected on direct calls. The gRPC layer also fences requests; this keeps direct tests and future in-process callers honest.

type Service

type Service struct {
	// contains filtered or unexported fields
}

Service wraps a backend transport.Service and exposes it as one active model slot. The wrapped backend still owns native inference; this layer owns residency cardinality, generation fencing, and switch/unload safety.

func New

func New(backend transport.Service, opts ...Option) *Service

New returns a transport service that allows only one active resident model.

func (*Service) Describe

func (s *Service) Describe(ctx context.Context, req transport.OpenSessionRequest) (transport.ModelInfo, error)

func (*Service) Embed

func (s *Service) Embed(ctx context.Context, req transport.EmbedRequest) (transport.EmbedResult, error)

func (*Service) LoadModel

func (s *Service) LoadModel(ctx context.Context, req transport.LoadModelRequest) (transport.ActiveModel, error)

func (*Service) OpenSession

func (s *Service) OpenSession(ctx context.Context, req transport.OpenSessionRequest) (transport.Session, error)

func (*Service) Status

func (s *Service) Status(ctx context.Context) (transport.DaemonStatus, error)

func (*Service) UnloadModel

func (s *Service) UnloadModel(ctx context.Context, req transport.UnloadModelRequest) error