DSSD (Speculative decoding): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 0 beat it on benchmarks — #100 of 151 most-superseded. Sub-problem: cluster led by EdgeLLM. Newer alternatives in the same sub-problem include PipeSD, DiP-SD, PicoSpec.

Superseded baseline#100 of 151 most-superseded

DSSD

Speculative decoding

superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites DSSD as a baseline.

“While DSSD ning2025dssdreduces uplink data through local re-sampling, it remains a serial "stop-and-wait" architecture strictly bound by network RTT.”
— A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.

PipeSD PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
May 13, 2026
DiP-SD DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge
Apr 22, 2026
PicoSpec A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
Mar 19, 2026