Is FlexDraft superseded?

FlexDraft (Speculative decoding): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline.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 EAGLE-3. Newer alternatives in the same sub-problem include D^2SD, TreeFlash, Hybrid Verified Decoding, Bastion, Draft-OPD.

Speculative decoding

FlexDraft

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration

On the frontierfirst seen May 19, 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Current frontier — recent, not yet superseded in the knowledge base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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

D^2SDD^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
Jun 3, 2026
TreeFlashTreeFlash: Parallel AR-Approximation for Faster Speculative Decoding
Jun 2, 2026
Hybrid Verified DecodingHybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
May 31, 2026
BastionBastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
May 28, 2026
Draft-OPDDraft-OPD: On-Policy Distillation for Speculative Draft Models
May 28, 2026
DominoDomino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
May 28, 2026
FlexDraftFlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
May 19, 2026
GraftDraft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
May 19, 2026
PARD-2PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
May 9, 2026
SpecBlockSpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
May 8, 2026
EVICTMaking Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
May 1, 2026
ConFuConFu: Contemplate the Future for Better Speculative Sampling
Apr 21, 2026