{"list":"closest","total":63,"rows":[{"id":"2502.18779","title":"Towards Optimal Multi-draft Speculative Decoding","created":"2025-02-26","cited_by_count":19},{"id":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59},{"id":"2412.18934","title":"Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference","created":"2024-12-25","cited_by_count":13},{"id":"2412.12639","title":"Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree","created":"2024-12-17","cited_by_count":20},{"id":"2412.00061","title":"Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration","created":"2024-11-25","cited_by_count":15},{"id":"2411.11055","title":"FastDraft: How to Train Your Draft","created":"2024-11-17","cited_by_count":6},{"id":"2411.05289","title":"SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding","created":"2024-11-08","cited_by_count":10},{"id":"2411.03786","title":"The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation","created":"2024-11-06","cited_by_count":14},{"id":"2411.00841","title":"A Theoretical Perspective for Speculative Decoding Algorithm","created":"2024-10-30","cited_by_count":29},{"id":"2410.21951","title":"Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding","created":"2024-10-29","cited_by_count":17},{"id":"2410.17375","title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration","created":"2024-10-22","cited_by_count":14},{"id":"2410.11744","title":"DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure","created":"2024-10-15","cited_by_count":25},{"id":"2410.11305","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","created":"2024-10-15","cited_by_count":18},{"id":"2410.06916","title":"SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration","created":"2024-10-09","cited_by_count":72},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22},{"id":"2410.03804","title":"Mixture of Attentions For Speculative Decoding","created":"2024-10-04","cited_by_count":17},{"id":"2410.01028","title":"Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity","created":"2024-10-01","cited_by_count":8},{"id":"2409.16560","title":"Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference","created":"2024-09-25","cited_by_count":5},{"id":"2409.00142","title":"Dynamic Depth Decoding: Faster Speculative Decoding for LLMs","created":"2024-08-30","cited_by_count":20},{"id":"2408.15766","title":"Learning Harmonized Representations for Speculative Sampling","created":"2024-08-28","cited_by_count":72},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91},{"id":"2408.11850","title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","created":"2024-08-13","cited_by_count":85},{"id":"2407.16207","title":"Graph-Structured Speculative Decoding","created":"2024-07-23","cited_by_count":4},{"id":"2407.11798","title":"PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation","created":"2024-07-16","cited_by_count":14},{"id":"2407.09722","title":"Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference","created":"2024-07-12","cited_by_count":11},{"id":"2406.18200","title":"SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding","created":"2024-06-26","cited_by_count":9},{"id":"2406.17276","title":"OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure","created":"2024-06-25","cited_by_count":67},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370},{"id":"2406.11016","title":"Optimized Speculative Sampling for GPU Hardware Accelerators","created":"2024-06-16","cited_by_count":2},{"id":"2406.03853","title":"Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism","created":"2024-06-06","cited_by_count":32},{"id":"2406.02532","title":"SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices","created":"2024-06-04","cited_by_count":46},{"id":"2405.19715","title":"SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths","created":"2024-05-30","cited_by_count":75},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38},{"id":"2404.18911","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","created":"2024-04-29","cited_by_count":58},{"id":"2404.15778","title":"BASS: Batched Attention-optimized Speculative Sampling","created":"2024-04-24","cited_by_count":11},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102},{"id":"2404.08698","title":"Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding","created":"2024-04-10","cited_by_count":23},{"id":"2403.10444","title":"Block Verification Accelerates Speculative Decoding","created":"2024-03-15","cited_by_count":30},{"id":"2403.09919","title":"Recurrent Drafter for Fast Speculative Decoding in Large Language Models","created":"2024-03-14","cited_by_count":37},{"id":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72},{"id":"2402.14160","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","created":"2024-02-21","cited_by_count":27},{"id":"2402.13720","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","created":"2024-02-21","cited_by_count":25},{"id":"2402.13485","title":"ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding","created":"2024-02-21","cited_by_count":12},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103},{"id":"2402.11809","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","created":"2024-02-19","cited_by_count":22},{"id":"2402.11131","title":"Speculative Streaming: Fast LLM Inference without Auxiliary Models","created":"2024-02-16","cited_by_count":38},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2312.11462","title":"Cascade Speculative Drafting for Even Faster LLM Inference","created":"2023-12-18","cited_by_count":83},{"id":"2311.13581","title":"PaSS: Parallel Speculative Sampling","created":"2023-11-22","cited_by_count":49},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150},{"id":"2310.15141","title":"SpecTr: Fast Speculative Decoding via Optimal Transport","created":"2023-10-23","cited_by_count":129},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165},{"id":"2310.07177","title":"Online Speculative Decoding","created":"2023-10-11","cited_by_count":113},{"id":"2310.05424","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","created":"2023-10-09","cited_by_count":80},{"id":"2308.04623","title":"Accelerating LLM Inference with Staged Speculative Decoding","created":"2023-08-08","cited_by_count":151},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2203.16487","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","created":"2022-03-30","cited_by_count":171}],"next_cursor":null}