SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding

Kunjun Li, Wenhao Chai, Yihao Liang, Yuezhou Hu, Shuyao Xu, Yi Pan, William X. Zheng, Kannan Ramchandran, Kurt Keutzer, Jiantao Jiao

SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding: 15 upvotes on Hugging Face Daily Papers, #16 of 46 papers on 2026-11-04. Day-by-day upvote history.

Upvotes over time

It had 15 upvotes by its first day, 15 upvotes by the next day, 15 upvotes by day 3, 15 upvotes by day 7, and has 15 now. It ranked #49 of 130 papers in its week and #49 of 130 in its month. Its code repository has 82 GitHub stars.

Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass. However, it remains unclear whether their released systems (stock) attain the full speedup that parallel drafting permits. We identify three challenges. First, with one request, each step accepts few tokens but reads every target weight. Second, with batching, per-request verification work roughly halves the speedup over autoregressive (AR) decoding. Third, speculative decoding is deployment-specific, and no universal optimization fits every serving regime, drafter, target model and GPU. To address these challenges, we present SpecPilot, an autonomous agentic loop that discovers algorithms and systems optimizations for each deployment. In each round, a cost model locates the largest gaps between the current system and its ceiling. Parallel agents explore directions and integrate the successful ones. Token forcing checks every output token against stock to detect reward hacking. A structured memory carries validated mechanisms to new rounds and deployments. SpecPilot discovered a general lossless 12-bit weight format, tree verification for hybrid recurrent targets, two-level verification and three batching mechanisms. We evaluate it across four target models, three drafters, two GPU platforms and five benchmarks. Without training or quality loss, it raises the speedup over AR from stock's 4.46times to 10.87times with one request, and from 1.94times to 3.93times with batching.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.