specific method · filed under inference & serving
MTP-1 speculative decoding
A one-token MTP speculative-decoding configuration recommended in the evidence for low-concurrency, latency-sensitive workloads.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
For latency-sensitive workloads at low concurrency, enable MTP-1 speculative decoding and disable prefix caching.
usedinference servingin vLLMvLLM
Filed alongside
Other methods under inference & serving :: decoding strategy.
Speculative decodingMulti-Token PredictionDSparkEAGLEDFlashPresence PenaltyBest-of-N scaffoldingNEXTN speculative decodingMulti-layer EAGLESpeculative samplingStandardized sampling configurationMulti-stage candidate filteringRecursive shared MTP-head draftingTask-specific sampling parametersChat Prefix CompletionConcurrency-aware draft-length tuningDistribution-matched draft-model fine-tuningEAGLE-3-style draft-model fine-tuningFused recurrent replay kernelGrammar-constrained decodingKV-cache sharing between drafter and targetLongest-trace selectionSame-checkpoint target and draft weightsThroughput-aware dynamic verification-length scheduling