4 papers
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang +15
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OPD), and sampling-heavy evalua…
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Yuhao Shen, Tianyu Liu, Xinyi Hu +9
Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, recent methods construct expansive…
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
Xinyi Hu, Yuhao Shen, Baolin Zhang +6
Speculative Decoding promises to accelerate the inference of Large Language Models, yet its efficacy often degrades in production-grade serving. Existing evaluations typically over…
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
Tianyu Liu, Yuhao Shen, Xinyi Hu +8
Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existi…