Table of Contents

Property HasSpeculativeDecodingDrafts

Namespace
LMKit.Model
Assembly
LM-Kit.NET.dll

HasSpeculativeDecodingDrafts

Indicates whether this model carries speculative-decoding draft assets that were loaded and can drive draft-and-verify decoding. This is true when either the checkpoint declares Multi-Token Prediction (MTP) heads (GGUF key <arch>.nextn_predict_layers, present on architectures such as Qwen 3.5 / 3.6, GLM-4.x, DeepSeek V3 / R1, BailingMoE2, and ExaOne-MoE) and those heads were loaded, or a DraftModel is attached (including one shipped inside the model envelope). Returns false when the packaged draft assets were skipped at load time via EnableSpeculativeDecodingDrafts = false.

public bool HasSpeculativeDecodingDrafts { get; }

Property Value

bool

Remarks

This reports the presence of draft assets, not whether speculative decoding will run end to end: the backend still performs a final tokenizer-compatibility check at context-creation time and falls back to single-token decoding when a draft source is incompatible.

Share