Table of Contents

Namespace LMKit.Inference

Namespaces

LMKit.Inference.Vision

Classes

InferencePolicies

Represents the configuration policies for inference processes.

Interfaces

IKVCache

Contract for objects that own an inference KV-cache whose residency in memory can be observed and, optionally, hibernated to disk.

Enums

ContextOverflowPolicy

Specifies strategies to handle scenarios when the context exceeds its allowed size.

ContextResidency

Tracks where the underlying inference context currently resides across its lazy-init / in-memory / hibernated lifecycle.

HibernationMode

Controls when the runtime hibernates an inference context at the end of a conversation turn. The mode is set on HibernationMode by the owning conversation (e.g. MultiTurnConversation, PdfChat) and consulted by the inference backend every time a usage lock is released.

InferenceModality

Specifies which modality (or combination of modalities) should be used when performing inference on the input data.

InputLengthOverflowPolicy

Defines strategies to adopt when the prompt length exceeds the context size.

Share