activity
20222026
most citedSpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

101 citations · 150 across the 9 of their papers we have counts for

collaborators

10 papers

cs.DC2026

Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel

Hongyi Jin, Bohan Hou, Guanjie Wang +18

Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter-kernel parallelism. Recent me…

cs.DC2025★ 1 cited

MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs

Xinhao Cheng, Zhihao Zhang, Yu Zhou +17

We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kerne…

cs.LG2025

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Rui Pan, Yinwei Dai, Zhihao Zhang +3

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs).…

cs.LG2025

Communication Bounds for the Distributed Experts Problem

Zhihao Jia, Qi Pang, Trung Tran +3

In this work, we study the experts problem in the distributed setting where an expert's cost needs to be aggregated across multiple servers. Our study considers various communicati…

cs.CL2025

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding

Zikun Li, Zhuofu Chen, Remi Delacourt +11

Modern large language model (LLM) applications exhibit diverse service-level objectives (SLOs), from low-latency requirements in interactive coding assistants to more relaxed const…

cs.LG2024

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Lijie Yang, Zhihao Zhang, Zhuofu Chen +2

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the e…