PEARL: Parallel Speculative Decoding with Adaptive Draft Length
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:4R36P3X6record.jsonopen to challenge →
read the original abstract
Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However, existing SD methods suffer from the mutual waiting problem, i.e., the target model gets stuck when the draft model is guessing tokens, and vice versa. This problem is directly incurred by the asynchronous execution of the draft model and the target model and is exacerbated due to the fixed draft length in speculative decoding. To address these challenges, we propose a conceptually simple, flexible, and general framework to boost speculative decoding, namely Parallel spEculative decoding with Adaptive dRaft Length (PEARL). Specifically, PEARL proposes pre-verify to verify the first draft token in advance during the drafting phase, and post-verify to generate more draft tokens during the verification phase. PEARL parallels the drafting phase and the verification phase via applying the two strategies, and achieves adaptive draft length for different scenarios, which effectively alleviates the mutual waiting problem. Experiments on various text generation benchmarks demonstrate the effectiveness of our PEARL, leading to a superior speed up performance up to 4.43$\times$ and 1.50$\times$, compared to auto-regressive decoding and vanilla speculative decoding, respectively. Our code is available at https://github.com/smart-lty/ParallelSpeculativeDecoding.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
BASTION is a budget-aware speculative decoding framework with adaptive tree-structured block diffusion drafting that reports up to 6.61x speedup and 39% improvement over block-diffusion baselines.
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware ...
-
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
A 1D token interface with Selective Token Editing improves multimodal image fusion by modeling global appearance factors separately from local 2D structures, yielding best overall performance on four benchmarks.
-
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
PPOW uses window-level RL with cost-aware speedup and proximity rewards plus adaptive divergence-aware windowing to reach 6.29-6.52 acceptance lengths and 3.39-4.36x speedups in speculative decoding.
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-19% higher speedup than EAGLE-3 in LLM speculative decoding by using repeated block expansions with hidden-state inheritance, a dynamic rank head, and a valid-prefix training mask.
-
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
KV cache reuse improves long-range draft acceptance in speculative decoding but delivers only marginal end-to-end speedups due to drafter limitations.
-
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
KV cache reuse improves long-range draft acceptance rates in speculative decoding but delivers only marginal end-to-end speedups because shallow drafters cannot accurately estimate target queries and receive sparse gr...
-
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding
A ReRAM-on-logic stacked chip delivers 14.08-135.69 tokens/s LLM inference with block-clustered compression and adaptive parallel speculative decoding, yielding 4.46-7.17x speedup over standard methods.
-
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
ECHO uses sparse gating and elastic budget pivoting in a super-tree structure to achieve up to 5.35x speedup for LLM inference under high concurrency.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.