Model techniques map
Techniquesinference & servingdecoding strategy

specific method · filed under inference & serving

DSpark

A speculative-decoding architecture that combines semi-autoregressive draft generation with confidence-scheduled verification.

Also called DSpark speculative decoding, DSpark speculative-decoding module, DSpark speculative decoding architecture.

sources
8
models
5
labs adopt it
2
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 4used 5core 1

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

10 spans quoted from the sources, strongest treatment first.

We equip DeepSeek-V4.1-Flash with DSpark (Cheng et al., 2026a), a speculative decoding module that combines semi-autoregressive drafting with confidence-scheduled verification.

coreunclearin DeepSeek-V4.1-FlashDeepSeek

The repo has the DSpark speculative-decoding module attached

usedinference servingin DeepSeek-V4-FlashDeepSeek

We also introduce the DSpark (Cheng et al., 2026a) speculative decoding architecture to improve decoding efficiency through semi-autoregressive draft generation and confidence-scheduled verification.

usedinference servingin DeepSeek-V4.1-FlashDeepSeek

We omit the MTP module during backbone pre-training and use DSpark (Cheng et al., 2026a) for speculative decoding.

usedinference servingin DeepSeek-V4.1-FlashDeepSeek

DSpark speculative decoding is enabled with a single flag

usedinference servingin DeepSeek-V4-Flash-0731DeepSeek

DSpark speculative decoding (semi-autoregressive draft generation with confidence-scheduled verification)

usedinference servingin DeepSeek-V4.1-FlashDeepSeek

Beyond MTP, two draft models are provided with Nemotron 3.5 Lightning: DSpark, which is recommended for DGX Spark inference workloads and low concurrency data center workloads.

optionalinference servingin Nemotron 3.5 LightningNVIDIA

DSpark: A semi-autoregressive speculative-decoding drafter that proposes a whole block of candidate tokens in a single forward pass from a parallel backbone.

optionalinference servingin Nemotron 3.5 LightningNVIDIA

Enable DSpark with --speculative-algorithm DSPARK

optionalinference servingin DeepSeek-V4-Flash-Vision-ExpDeepSeek

DSpark speculative decoding is enabled with a single flag

optionalinference servingin DeepSeek-V4-Pro-0813DeepSeek

Filed alongside

Other methods under inference & serving :: decoding strategy.