Property HasSpeculativeDecodingDrafts
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
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.