DDD (Speculative decoding): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 4 beat it on benchmarks — #20 of 151 most-superseded. Sub-problem: cluster led by EAGLE-3. Newer alternatives in the same sub-problem include D^2SD, TreeFlash, Hybrid Verified Decoding, Bastion, Draft-OPD.

Speculative decoding

DDD

Superseded baseline#20 of 151 most-superseded

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 4 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating DDD. Values are copied from the source paper's tables — verify against the cited paper.

ECHO beats DDD
5.25 vs 3.97
Avg. Speedup · [Vicuna-13B]
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
EVICT beats DDD
147.69 vs 112.25
Average · [Temperature = 0]
Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
method beats DDD
5.41 vs 4.97
Avg. Speedup · [Vicuna-13B]
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
LDLP-DDD beats DDD
71.20 vs 69.39
Tok/s · [GSM8K]
AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.