SDFP (Speculative decoding): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by SpecInfer. Newer alternatives in the same sub-problem include SpecKV, FASER, ConfLayers, Goose, greedy multi-path block verification (GBV).

Speculative decoding

SDFP

SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration

On the frontierfirst seen Feb 5, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

SpecKVSpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
May 4, 2026
FASERFASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving
Apr 22, 2026
ConfLayersConfLayers: Adaptive Confidence-based Layer Skipping for Self-Speculative Decoding
Apr 16, 2026
GooseGoose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
Apr 2, 2026
greedy multi-path block verification (GBV)Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling
Feb 18, 2026
SDFPSDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration
Feb 5, 2026
PacerPACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length
Feb 1, 2026
CAS-Spec (Cascade Adaptive Self-Speculative Decoding)CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
Oct 30, 2025
FastVLMFastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
Oct 26, 2025
sd.npuAccelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution
Oct 17, 2025
HiSpecHiSpec: Hierarchical Speculative Decoding for LLMs
Oct 1, 2025