SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length $γ$, which determines how many tokens the draft model proposes per step. Nearly all existing systems use a fixed $γ$ (typically 4), yet empirical evidence suggests that the optimal value varies across task types and, crucially, depends on the compression level applied to the target model. In this paper, we present SpecKV, a lightweight adaptive controller that selects $γ$ per speculation step using signals extracted from the draft model itself. We profile speculative decoding across 4 task categories, 4 speculation lengths, and 3 compression levels (FP16, INT8, NF4), collecting 5,112 step-level records with per-step acceptance rates, draft entropy, and draft confidence. We demonstrate that the optimal $γ$ shifts across compression regimes and that draft model confidence and entropy are strong predictors of acceptance rate (correlation $\approx$ 0.56). SpecKV uses a small MLP trained on these signals to maximize expected tokens per speculation step, achieving a 56.0% improvement over the fixed-$γ=4$ baseline with only 0.34 ms overhead per decision (<0.5% of step time). The improvement is statistically significant (p < 0.001, paired bootstrap test). We release all profiling data, trained models, and notebooks as open-source artifacts.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
Large Language Models (LLMs) have revolutionized natural language processing tasks, but their deployment in datacenter environments faces significant challenges due to the massive memory requirements of key-value (KV) ca…
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verification by a larger target model. In practice, speculative efficiency i…
Reinforcement LearningDREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We intr…
feature selectionNightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades perform…
S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices
Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Experts (MoE) have been proposed to improve in…