Cover Image

Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Rui, Chen, Zhuofu, Liu, Hongyi, Krishnamurthy, Arvind, Netravali, Ravi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aragog: Just-in-Time Model Routing for Scalable Serving of Agentic Workflows
by: Dai, Yinwei, et al.
Published: (2025)

Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
by: Dai, Yinwei, et al.
Published: (2023)

FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
by: Li, Yuchen, et al.
Published: (2026)

SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism
by: Shen, Yuhao, et al.
Published: (2025)

Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
by: Wei, Jinhui, et al.
Published: (2025)

Accelerating OpenPangu Inference on NPU via Speculative Decoding
by: Dai, Yuntao, et al.
Published: (2026)

A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
by: Zhang, Yida, et al.
Published: (2026)

Marconi: Prefix Caching for the Era of Hybrid LLMs
by: Pan, Rui, et al.
Published: (2024)

FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving
by: Chen, Wenyan, et al.
Published: (2026)

Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving
by: Pagonas, Nikos, et al.
Published: (2025)

Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
by: Wang, Zhibin, et al.
Published: (2025)

SLOs-Serve: Optimized Serving of Multi-SLO LLMs
by: Chen, Siyuan, et al.
Published: (2025)

Design a Win-Win Strategy That Is Fair to Both Service Providers and Tasks When Rejection Is Not an Option
by: Trabelsi, Yohai, et al.
Published: (2024)

Kairos: A Scalable Serving System for Physical AI
by: Dai, Yinwei, et al.
Published: (2026)

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
by: Chen, Liangkun, et al.
Published: (2025)

GoodSpeed: Optimizing Fair Goodput with Adaptive Speculative Decoding in Distributed Edge Inference
by: Tran, Phuong, et al.
Published: (2025)

Make Every Draft Count: Hidden State based Speculative Decoding
by: Chen, Yuetao, et al.
Published: (2026)

MineDraft: A Framework for Batch Parallel Speculative Decoding
by: Tang, Zhenwei, et al.
Published: (2026)

Persistent HyTM via Fast Path Fine-Grained Locking
by: Coccimiglio, Gaetano, et al.
Published: (2025)

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation
by: Cheng, Rongxin, et al.
Published: (2025)

Wherefore Art Thou? Provenance-Guided Automatic Online Debugging with Lumos
by: Chen, Jingyuan, et al.
Published: (2026)

PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
by: Han, Yunhe, et al.
Published: (2026)

Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
by: Venkatesha, Yeshwanth, et al.
Published: (2025)

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
by: Li, Rui, et al.
Published: (2025)

GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
by: Ye, Fanjiang, et al.
Published: (2026)

ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
by: Chen, Qiaoling, et al.
Published: (2025)

RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
by: Wu, Yongji, et al.
Published: (2025)

FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
by: Liu, Xing, et al.
Published: (2025)

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding
by: Zhang, Ziyi, et al.
Published: (2025)

FLASH Viterbi: Fast and Adaptive Viterbi Decoding for Modern Data Systems
by: Deng, Ziheng, et al.
Published: (2025)

A System for Microserving of LLMs
by: Jin, Hongyi, et al.
Published: (2024)

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput
by: Song, Jingwei, et al.
Published: (2025)

Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding
by: Bhatia, Nidhi, et al.
Published: (2025)

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
by: Abramovich, Talor, et al.
Published: (2026)

FailSafe: High-performance Resilient Serving
by: Xu, Ziyi, et al.
Published: (2025)

NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning
by: Wang, Irene, et al.
Published: (2026)

SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models
by: Chen, Fahao, et al.
Published: (2025)

SpecMemo: Speculative Decoding is in Your Pocket
by: Yildirim, Selin, et al.
Published: (2025)

Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution
by: Wang, Siqi, et al.
Published: (2024)

SFVInt: Simple, Fast and Generic Variable-Length Integer Decoding using Bit Manipulation Instructions
by: Liao, Gang, et al.
Published: (2024)