AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem

Seongjin Cha, Gyuwan Kim, Dongsu Han, Tao Yang, Insu Han

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: KV cache eviction and compression · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use TPT instead of acceptance rate as the predictor of throughput (ablation)KnapSpec · GovReport 12K-13K tokensPearson correlation with throughput: 0.538 -> 0.837Improved
add cosine-similarity pruning threshold tau=0.5 (ablation)KnapSpec · GovReportspeedup / memory: 1.26x speedup retained, memory reduced by 31%Improved
raise pruning threshold beyond 0.5 (ablation)KnapSpec · Llama-3.1-8BspeedupHurt
increase optimization interval from 4 to 64 steps (ablation)KnapSpec · Qwen3-8Boptimization overhead: 40.9% -> 7.5%Improved
increase optimization interval beyond 64 steps (128, 256) (ablation)KnapSpec · Qwen3-8Bthroughput: peak 18.1 tok/s at 64Hurt
replace DEL/SWIFT/CLaSp with KnapSpec layer selectionself-speculative decoding · GovReportspeedup: 1.33x (SWIFT), 1.22x (CLaSp) -> 1.47xImproved
replace greedy decoding with nucleus samplingKnapSpec · AIME24speedup: 1.28 -> 1.13Mixed
use KnapSpec on other GPUs (RTX A6000 vs RTX 6000 Pro)KnapSpec · GovReport Llama-3.1-8Bspeedup: 1.27x -> 1.28xNo clear effect
use DEL early-exit on base modelsself-speculative decoding · GovReport Llama3.1-70Bspeedup: 1.00x -> 0.87xHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy