Model Serving · Data artifact

Speculative Decoding Configuration

Data artifactModel ServingModelsarc:SpeculativeDecodingConfig

A configuration selecting the draft model, target model and speculation window length for speculative decoding.

Responsibility. Fixes draft-target pairing and speculation window.

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Speculative Decoder Ch4.4 Ch7.1A
Speculative Draft Model abstract Ch4.4

is written by dependency

Draft Length Controller Ch7.1A

Quantitative guidance

As stated by the sources; verify before use.

Production windows typically 4-8 tokens, averaging 4-5 accepted tokens per target pass (Ch4.4).

Sources

Ch4.4: T. Nguyen, "Performance Profiling and Optimization," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.4. ISBN: 9798244538229.
Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.