Skip to yearly menu bar Skip to main content


Timezone: US/Pacific
Full Schedule Mon Tue Wed Thu Fri
Filter Events
Registration Desk
8:00 AM - 5:00 PM
Oral
8:30 AM - 10:00 AM
6 Events in this session
ADR: AN AGENTIC DETECTION SYSTEMFORENTERPRISE AGENTIC AI SECURITY
Chenning Li ⋅ Pan Hu ⋅ Justin Xu ⋅ Baris Ozbas ⋅ Olivia Liu ⋅ Caroline Van ⋅ Manxue Li ⋅ Wei Zhou ⋅ Mohammad Alizadeh ⋅ Pengyu Zhang ⋅ KK Sriramadhesikan ⋅ Ming Zhang
PROMPTS: PeRformance Optimization via Multi-Agent Planning for LLM Training and Serving
Yuran Ding ⋅ Ruobing Han ⋅ Xiaofan Zhang ⋅ Xinwei Chen
Agentic Operator Generation for ML ASICs
Alec Hammond ⋅ Aram Markosyan ⋅ Aman Dontula ⋅ Simon Mahns ⋅ Zacharias Fisches ⋅ Dmitrii Pedchenko ⋅ Keyur Muzumdar ⋅ Natacha Supper ⋅ Site Cao ⋅ Haishan Zhu ⋅ Mark Saroufim ⋅ Joe Isaacson ⋅ Laura Wang ⋅ Warren Hunt ⋅ Kaustubh Gondkar ⋅ Roman Levenstein ⋅ Gabriel Synnaeve ⋅ Richard Li ⋅ Jacob Kahn ⋅ Ajit Mathews
Cost-aware Duration Prediction for Software Upgrades in Datacenters
Yi Ding ⋅ Aijia Gao ⋅ Thibaud Ryden ⋅ Michal Sedlak ⋅ Essam Ewaisha ⋅ Igor Marnat ⋅ Henry (Hank) Hoffmann
The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
Xingyao Wang ⋅ Simon Rosenberg ⋅ Juan Michelini ⋅ Calvin Smith ⋅ Hoang Tran ⋅ Engel Nyst ⋅ Rohit Malhotra ⋅ Xuhui Zhou ⋅ Valerie Chen ⋅ Robert Brennan ⋅ Graham Neubig
BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
Zhen Zheng ⋅ Xin Ji ⋅ Taosong Fang ⋅ Fanghao Zhou ⋅ Chuanjie Liu ⋅ Gang Peng
Go to Event Page
Oral
8:30 AM - 10:00 AM
5 Events in this session
PRISM: Parametrically Refactor Inference for Speculative Decoding Draft Models
Xuliang Wang ⋅ Yuetao Chen ⋅ Maochan Zhen ⋅ Fang LIU ⋅ Xinzhou Zheng ⋅ Xingwu Liu ⋅ Hong Xu ⋅ Ming Li
CDLM: Consistency Diffusion Language Models for Faster Sampling
Minseo Kim ⋅ Chenfeng Xu ⋅ Coleman Hooper ⋅ Harman Singh ⋅ Ben Athiwaratkun ⋅ Ce Zhang ⋅ Kurt Keutzer ⋅ Amir Gholami
Speculative Decoding: Performance or Illusion?
Xiaoxuan Liu ⋅ Jiaxiang Yu ⋅ Jongseok Park ⋅ Ion Stoica ⋅ Alvin Cheung
SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
Jameson Sandler ⋅ Jacob K Christopher ⋅ Tom Hartvigsen ⋅ Ferdinando Fioretto
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
Yilong Zhao ⋅ Jiaming Tang ⋅ Kan Zhu ⋅ Zihao Ye ⋅ Chi-Chih Chang ⋅ Chaofan Lin ⋅ Jongseok Park ⋅ Guangxuan Xiao ⋅ Mohamed Abdelfattah ⋅ Mingyu Gao ⋅ Baris Kasikci ⋅ Song Han ⋅ Ion Stoica
Go to Event Page
Invited Talk
10:30 AM - 11:30 AM

Large language model training follows a standard pipeline:x000D tokenization, pretraining, possibly mid-training, and post training orx000D alignment. Despite its wild success, we understand relatively littlex000D about this recipe and are almost certainly missing many opportunitiesx000D to improve it. In this talk, I will focus on three such cases. I’llx000D describe our work on data efficient post training (e.g. LIMA, ALMA,x000D and s1) where we argue that nearly all advanced model capabilitiesx000D ultimately come from the pretraining data, even if effective alignmentx000D is still essential for controlling model behavior. I will alsox000D describe new methods for extracting more signal from the pretrainingx000D data, including new hierarchical architectures for byte-level languagex000D models (e.g. BLT) that are both tokenizer-free and scale better thanx000D traditional BPE-based methods, especially in the long tail. Finally, Ix000D will discuss decentralized, modular training algorithms (e.g. BTM)x000D that better isolate and control the influence of specific data onx000D specific model components and behaviors. Together, these methodsx000D promise to simplify training and improve scaling, by centering andx000D amplifying the influence of data in architecture design.

... more
Speaker Bio
Luke Zettlemoyer
Luke Zettlemoyer is a Professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington and a Senior Research Director at Meta. His research interests are in the intersections of natural language processing, machine learning, and decision making under uncertainty, with a recent emphasis on the science of training both text-based and multi-modal language models. Luke did postdoctoral research at the University of Edinburgh, earned his PhD at MIT, and was an undergraduate at NC State University. His honors include numerous paper awards, being named a Schmidt AI 2050 Senior Follow in 2025, elected President of the Association for Computational Linguistics (ACL) in 2024, named a Fellow of the ACL in 2021 along with winning the Presidential Early Career Award for Scientists and Engineers (PECASE) award in 2016, an Allen Distinguished Investigator Award in 2014, and the National Science Foundation (NSF) International Research Fellowship in 2009.
... more
Session
10:30 AM - 11:30 AM
Oral
1:00 PM - 2:15 PM
5 Events in this session
SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving
Andrew Bitar ⋅ Aravind Vayalapra ⋅ Baorui Zhou ⋅ Matthew Boyd ⋅ Charlie Wang ⋅ Sahil Parmar ⋅ Eugene Sha ⋅ Gautam Rayaprolu ⋅ Peter Hicks ⋅ Alex Bowe ⋅ Roberto DiCecco ⋅ Santosh Raghavan ⋅ Evan Patrick ⋅ Josip Smolcic ⋅ David Han ⋅ Kris Kang ⋅ Andy Rock ⋅ Josh Hay ⋅ Mohamed Eldafrawy ⋅ Mikhail Kandel ⋅ Daulet Zhanguzin ⋅ Omar Kilani ⋅ Liming Gong ⋅ Andrew Paprotskyi ⋅ Arash Taheri-Dezfouli ⋅ Josh Fender ⋅ Andrew Ling
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
Tiyasa Mitra ⋅ Ritika Borkar ⋅ Nidhi Bhatia ⋅ Shivam Raj ⋅ hongkuan zhou ⋅ Yan Ru Pei ⋅ Vishwanath Venkatesan ⋅ Kyle Kranen ⋅ Ramon Matas ⋅ Dheevatsa Mudigere ⋅ Ritchie Zhao ⋅ Maximilian Golub ⋅ Arpan Dutta ⋅ Suresh Nambi ⋅ Sailaja Madduri ⋅ Dharmesh Jani ⋅ Brian Pharris ⋅ Itay Neeman ⋅ Bita Darvish Rouhani
Optimizing Deployment Configurations for LLM Inference
Sungmin Cho ⋅ Jaewon Lee ⋅ Chunqiang Tang ⋅ Yejin Lee ⋅ Geonhwa Jeong ⋅ Anca Agape ⋅ Scott Batura ⋅ Vincent Boivin ⋅ Stephen Chen ⋅ Renfei Chen ⋅ Sijia Chen ⋅ Yan Cui ⋅ Bradley Davis ⋅ Summer Deng ⋅ Nick Egebo ⋅ Emad El-Haraty ⋅ Sebastien Estienne ⋅ Lu Fang ⋅ Lu Fang ⋅ Joshua Fromm ⋅ Raj Ganapathy ⋅ Vedanuj Goswami ⋅ Liangpeng Guo ⋅ Ye Hu ⋅ Chenheli Hua ⋅ Jianyu Huang ⋅ Aya Ibrahim ⋅ Niranjan Jagannath ⋅ Hongyi Jia ⋅ Changkyu Kim ⋅ Shikai Li ⋅ Brandon Liu ⋅ Jiawen Liu ⋅ Ajit Mathews ⋅ Xiaozhu Meng ⋅ Vlad Tiberiu Mihailescu ⋅ Amit Nagpal ⋅ Maxim Naumov ⋅ Michal Ostrowski ⋅ Jialin Ouyang ⋅ Jason Park ⋅ Sarunya Pumma ⋅ Ye Qi ⋅ Zixi Qi ⋅ Jeremy Francis Reizenstein ⋅ Rajasi Saha ⋅ Nandhini Santhanam ⋅ Zhan Shu ⋅ Ruan Silva ⋅ Grigory Sizov ⋅ Jon Swenson ⋅ Brandon Taylor ⋅ Chris Thi ⋅ Adolfo Victoria ⋅ Yunfan Wang ⋅ Pengchao Wang ⋅ Wenchen Wang ⋅ Xiaodong Wang ⋅ Bram Wasti ⋅ Wei Xu ⋅ Qirui Yang ⋅ Jingyi Yang ⋅ Hector Yuen ⋅ Zhengyuan Zhang ⋅ Jing Zhang ⋅ Yi Zhen ⋅ Yanjun Zhou
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
Nicholas Santavas ⋅ Kareem Eissa ⋅ Patrycja Cieplicka ⋅ Piotr Florek ⋅ Matteo Nulli ⋅ Stefan Vasilev ⋅ Seyyed Hashemi ⋅ Antonios Gasteratos ⋅ Shahram Khadivi
Scaling Up Large Language Models Serving Systems for Semantic Job Search
Kayhan Behdin ⋅ Qingquan Song ⋅ Sriram Vasudevan ⋅ Jian Sheng ⋅ Xiaojing Ma ⋅ Zhengze Zhou ⋅ Chuanrui Zhu ⋅ Guoyao Li ⋅ Chanh Nguyen ⋅ Sayan Ghosh ⋅ Hejian Sang ⋅ Ata Fatahi ⋅ Sundara Ramachandran ⋅ Xiaoqing Wang ⋅ Qing Lan ⋅ Vinay S ⋅ Qi Guo ⋅ Caleb Johnson ⋅ Zhipeng Wang ⋅ Fedor Borisyuk
Go to Event Page
Oral
1:00 PM - 2:15 PM
5 Events in this session
HELIOS : Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving
Avinash Kumar ⋅ Shashank Nag ⋅ Jason Clemons ⋅ LIZY JOHn ⋅ Poulami Das
IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
Wanli Zhong ⋅ Haibo Feng ⋅ Zirui Zhou ⋅ Hanyang Peng ⋅ Shiqi Yu
REPARO: LOSS-RESILIENT GENERATIVE CODEC FOR VIDEO CONFERENCING
Tianhong Li ⋅ Vibhaalakshmi Sivaraman ⋅ Pantea Karimi ⋅ Lijie Fan ⋅ Mohammad Alizadeh ⋅ Dina Katabi
Rethinking DVFS for Mobile LLMs: Unified Energy-Aware Scheduling with CORE
Zongpu Zhang ⋅ Pranab Dash ⋅ Qiang Xu ⋅ Y. Charlie Hu ⋅ Jian Li ⋅ Haibing Guan
EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence
Ansel Erol ⋅ Seungjun Lee ⋅ Divya Mahajan
Go to Event Page
Oral
2:45 PM - 4:15 PM
6 Events in this session
Sparing Strategies to Minimize Reliability Impact On Large Training Jobs
Kevin Quirk ⋅ Matthew Lennie ⋅ Ehsan K. Ardestani ⋅ Satyajeet Ahuja ⋅ Matthew Bergeron ⋅ Andrew Grier ⋅ Zhaodong Wang ⋅ Mustafa Ozdal ⋅ Xu Zhang ⋅ Abhinav Triguna ⋅ Ying Zhang ⋅ Mathew Oldham ⋅ Chunqiang Tang
veScale-FSDP: Flexible and High-Performance FSDP at Scale
Zezhou Wang ⋅ Youjie Li ⋅ Zhiqi Lin ⋅ Jiacheng Yang ⋅ Cong Xie ⋅ Guanyu Feng ⋅ ZHENG ZHONG ⋅ Ziyue Huang ⋅ Hongyu Zhu ⋅ Zhi Zhang ⋅ Yanghua Peng ⋅ Xin Liu
AXLearn: Modular, Hardware-Agnostic Large Model Training
Mark Lee ⋅ Chang Lan ⋅ Tom Gunter ⋅ John Peebles ⋅ Hanzhi Zhou ⋅ Xuan Zou ⋅ Sneha Bangalore ⋅ Chung-Cheng Chiu ⋅ Nan Du ⋅ Xianzhi Du ⋅ Philipp Dufter ⋅ Liang He ⋅ Ruixuan Hou ⋅ Haoshuo Huang ⋅ Dongseong Hwang ⋅ Xiang Kong ⋅ Jinhao Lei ⋅ Tao Lei ⋅ Meng Li ⋅ Li Li ⋅ Jiarui Lu ⋅ Zhiyun Lu ⋅ Yiping Ma ⋅ David Qiu ⋅ Vivek Rathod ⋅ Senyu Tong ⋅ Zhucheng Tu ⋅ Chong Wang ⋅ Jianyu Wang ⋅ Yongqiang Wang ⋅ Zirui Wang ⋅ Floris Weers ⋅ Sam Wiseman ⋅ Guoli Yin ⋅ Bowen Zhang ⋅ Xiyou Zhou ⋅ Danyang Zhuo ⋅ Cheng Leong ⋅ Ruoming Pang
GUARD: SCALABLE STRAGGLER DETECTION AND NODE HEALTH MANAGEMENT FOR LARGE-SCALE TRAINING
guanliang liu ⋅ Abhinandan Patni ⋅ congzhu lin ⋅ Zoe Zeng ⋅ Jack Wittmayer ⋅ Yinghong Liu ⋅ josh wu ⋅ Anthony Ko ⋅ Alexander Zhipa ⋅ Ashvin Nihalani ⋅ Binxuan Huang ⋅ Cong Cheng ⋅ Mi Sun ⋅ Vijay rajakumar ⋅ Rejith Joseph ⋅ Parthasarathy Govindarajen
MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs
Jiyuan Zhang ⋅ Yining Liu ⋅ Siqi Yan ⋅ Lisen Deng ⋅ Jennifer Cao ⋅ Shuqi Yang ⋅ Bi Xue ⋅ Min Ni ⋅ Shen Li
FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost
Chenhao Feng ⋅ Haoli Zhang ⋅ Shakhzod Ali-zade ⋅ Yanli Zhao ⋅ Liang Luo ⋅ Jennifer Cao ⋅ Lisen Deng ⋅ Siqiao Chen ⋅ Chenyu Zhao ⋅ Tristan Rice ⋅ Daniel Johnson ⋅ Min Si ⋅ Tiantu Xu ⋅ Yi Zhang ⋅ Evgenii Kolpakov ⋅ Siqi Yan ⋅ Chuanhao Zhuge ⋅ Min Ni ⋅ Bi Xue ⋅ Qunshu Zhang ⋅ Shen Li
Go to Event Page
Oral
2:45 PM - 4:15 PM
5 Events in this session
Massive-Scale Out-Of-Core UMAP on the GPU
Jinsol Park ⋅ Corey Nolet ⋅ Edward Raff ⋅ Tim Oates ⋅ Akira Naruse
Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference
Mengtian Yang ⋅ Zhekun Zhang ⋅ Mingheng Wu ⋅ jianwen yan ⋅ Hanshi Sun ⋅ Li-Wen Chang
Hawkeye: Reproducing GPU-Level Non-Determinism
Erez Badash ⋅ Dan Boneh ⋅ Ilan Komargodski ⋅ Megha Srivastava
DriftBench: Measuring and Predicting Infrastructure Drift in LLM Serving Systems
Gianluigi Vitale
PARROT: Persuasion and Agreement Robustness Rating of Output Truth — A Sycophancy Robustness Benchmark for LLMs
Özay Ezerceli ⋅ Mahmoud ElHussieni
Go to Event Page
Oral
4:30 PM - 6:00 PM
6 Events in this session
XProf: An Open, Scalable, and Extensible Profiling System for the Modern ML Stack
Robert Hundt ⋅ Naveen Kumar ⋅ Jose Baiocchi Paredes ⋅ Scott Goodson ⋅ Clive Verghese ⋅ Prasanna Rengasamy ⋅ Kelvin Le ⋅ Jiya Zhang ⋅ Charles Alaras ⋅ Yin Zhang ⋅ Kan Cai ⋅ Jiten Thakkar ⋅ Sai Ganesh Bandiatmakuri ⋅ Yogesh SY ⋅ Ani Udipi ⋅ Vikas Agarwal
AIRS: Scaling Live Inference in Resource Constrained Environments
Nilesh Jagnik ⋅ Xiaohao Yang ⋅ Tuan Do ⋅ Chelsea Chen ⋅ Harshvardhan GM
SAKURAONE: An Open Ethernet–Based AI HPC System and Its Observed Workload Dynamics in a Single-Tenant LLM Development Environment
Fumikazu KONISHI ⋅ Yuuki Tsubouchi ⋅ Hirofumi Tsuruta
MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
Srinivas ⋅ Andrey Balogh ⋅ Brad B ⋅ Brian Coutinho ⋅ Louis Feng ⋅ Sheng Fu ⋅ Sanshan Gao ⋅ Mehryar Garakani ⋅ Taekyung Heo ⋅ David Kanter ⋅ Josh Ladd ⋅ Ziwei Li ⋅ Winston Liu ⋅ Changhai Man ⋅ Dan Mihailescu ⋅ Spandan More ⋅ Joongun Park ⋅ Ashwin Ramachandran ⋅ Vinay Ramakrishnaiah ⋅ Saeed Rashidi ⋅ Vijay Janapa Reddi ⋅ Puneet Sharma ⋅ Phio Tian ⋅ William Won ⋅ Hanjiang Wu ⋅ Huan Xu ⋅ Jinsun Yoo ⋅ Tushar Krishna
ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler
Bohua Zou ⋅ Debayan Roy ⋅ Dhimankumar Airao ⋅ Weihao Xu ⋅ Binqi Sun ⋅ Yutao Liu ⋅ Haibo Chen
Machine Learning Fleet Efficiency: Improving TPU Systems at Scale with ML Productivity Goodput
Arissa Wongpanich ⋅ Tayo Oguntebi ⋅ Jose Baiocchi Paredes ⋅ Yu Wang ⋅ Phitchaya Phothilimthana ⋅ Ritwika Mitra ⋅ Zongwei Zhou ⋅ Naveen Kumar ⋅ Vijay Janapa Reddi
Go to Event Page
Oral
4:30 PM - 6:00 PM
6 Events in this session
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
Stuart H. Sul ⋅ Simran Arora ⋅ Benjamin Spector ⋅ Christopher Ré
Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel
Hongyi Jin ⋅ Bohan Hou ⋅ Guanjie Wang ⋅ Ruihang Lai ⋅ Jinqi Chen ⋅ Zihao Ye ⋅ Yaxing Cai ⋅ Yixin Dong ⋅ Xinhao Cheng ⋅ Zhihao Zhang ⋅ Yilong Zhao ⋅ Yingyi Huang ⋅ Lijie Yang ⋅ Jinchen Jiang ⋅ Gabriele Oliaro ⋅ Jianan Ji ⋅ Xupeng Miao ⋅ Vinod Grover ⋅ Todd Mowry ⋅ Zhihao Jia ⋅ Tianqi Chen
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang ⋅ Shaowei Zhu ⋅ Anjiang Wei ⋅ Zhenyu Song ⋅ Allen Nie ⋅ Zhen Jia ⋅ Nandita Vijaykumar ⋅ Yida Wang ⋅ Kunle Olukotun
DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling
Yi Pan ⋅ Yile Gu ⋅ Luo Jinbin ⋅ Yibo Wu ⋅ Ziren Wang ⋅ Hongtao Zhang ⋅ Ziyi Xu ⋅ Shengkai Lin ⋅ Baris Kasikci ⋅ Stephanie Wang
ApproxMLIR : Accuracy-Aware Compiler for Compound ML System
Hao Ren ⋅ Yi Mu ⋅ Sasa Misailovic
HipKittens: Fast and Furious AMD Kernels
William Hu ⋅ Drew Wadsworth ⋅ Sean Siddens ⋅ Stanley Winata ⋅ Daniel Fu ⋅ Ryan Swann ⋅ Muhammad Osama ⋅ Christopher Ré ⋅ Simran Arora
Go to Event Page
Poster
6:00 PM - 8:00 PM
52 Events in this session
ADR: AN AGENTIC DETECTION SYSTEMFORENTERPRISE AGENTIC AI SECURITY
Chenning Li ⋅ Pan Hu ⋅ Justin Xu ⋅ Baris Ozbas ⋅ Olivia Liu ⋅ Caroline Van ⋅ Manxue Li ⋅ Wei Zhou ⋅ Mohammad Alizadeh ⋅ Pengyu Zhang ⋅ KK Sriramadhesikan ⋅ Ming Zhang
PRISM: Parametrically Refactor Inference for Speculative Decoding Draft Models
Xuliang Wang ⋅ Yuetao Chen ⋅ Maochan Zhen ⋅ Fang LIU ⋅ Xinzhou Zheng ⋅ Xingwu Liu ⋅ Hong Xu ⋅ Ming Li
PROMPTS: PeRformance Optimization via Multi-Agent Planning for LLM Training and Serving
Yuran Ding ⋅ Ruobing Han ⋅ Xiaofan Zhang ⋅ Xinwei Chen
CDLM: Consistency Diffusion Language Models for Faster Sampling
Minseo Kim ⋅ Chenfeng Xu ⋅ Coleman Hooper ⋅ Harman Singh ⋅ Ben Athiwaratkun ⋅ Ce Zhang ⋅ Kurt Keutzer ⋅ Amir Gholami
Agentic Operator Generation for ML ASICs
Alec Hammond ⋅ Aram Markosyan ⋅ Aman Dontula ⋅ Simon Mahns ⋅ Zacharias Fisches ⋅ Dmitrii Pedchenko ⋅ Keyur Muzumdar ⋅ Natacha Supper ⋅ Site Cao ⋅ Haishan Zhu ⋅ Mark Saroufim ⋅ Joe Isaacson ⋅ Laura Wang ⋅ Warren Hunt ⋅ Kaustubh Gondkar ⋅ Roman Levenstein ⋅ Gabriel Synnaeve ⋅ Richard Li ⋅ Jacob Kahn ⋅ Ajit Mathews
Speculative Decoding: Performance or Illusion?
Xiaoxuan Liu ⋅ Jiaxiang Yu ⋅ Jongseok Park ⋅ Ion Stoica ⋅ Alvin Cheung
Cost-aware Duration Prediction for Software Upgrades in Datacenters
Yi Ding ⋅ Aijia Gao ⋅ Thibaud Ryden ⋅ Michal Sedlak ⋅ Essam Ewaisha ⋅ Igor Marnat ⋅ Henry (Hank) Hoffmann
SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
Jameson Sandler ⋅ Jacob K Christopher ⋅ Tom Hartvigsen ⋅ Ferdinando Fioretto
The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
Xingyao Wang ⋅ Simon Rosenberg ⋅ Juan Michelini ⋅ Calvin Smith ⋅ Hoang Tran ⋅ Engel Nyst ⋅ Rohit Malhotra ⋅ Xuhui Zhou ⋅ Valerie Chen ⋅ Robert Brennan ⋅ Graham Neubig
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
Yilong Zhao ⋅ Jiaming Tang ⋅ Kan Zhu ⋅ Zihao Ye ⋅ Chi-Chih Chang ⋅ Chaofan Lin ⋅ Jongseok Park ⋅ Guangxuan Xiao ⋅ Mohamed Abdelfattah ⋅ Mingyu Gao ⋅ Baris Kasikci ⋅ Song Han ⋅ Ion Stoica
HELIOS : Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving
Avinash Kumar ⋅ Shashank Nag ⋅ Jason Clemons ⋅ LIZY JOHn ⋅ Poulami Das
SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving
Andrew Bitar ⋅ Aravind Vayalapra ⋅ Baorui Zhou ⋅ Matthew Boyd ⋅ Charlie Wang ⋅ Sahil Parmar ⋅ Eugene Sha ⋅ Gautam Rayaprolu ⋅ Peter Hicks ⋅ Alex Bowe ⋅ Roberto DiCecco ⋅ Santosh Raghavan ⋅ Evan Patrick ⋅ Josip Smolcic ⋅ David Han ⋅ Kris Kang ⋅ Andy Rock ⋅ Josh Hay ⋅ Mohamed Eldafrawy ⋅ Mikhail Kandel ⋅ Daulet Zhanguzin ⋅ Omar Kilani ⋅ Liming Gong ⋅ Andrew Paprotskyi ⋅ Arash Taheri-Dezfouli ⋅ Josh Fender ⋅ Andrew Ling
IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
Wanli Zhong ⋅ Haibo Feng ⋅ Zirui Zhou ⋅ Hanyang Peng ⋅ Shiqi Yu
BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
Zhen Zheng ⋅ Xin Ji ⋅ Taosong Fang ⋅ Fanghao Zhou ⋅ Chuanjie Liu ⋅ Gang Peng
REPARO: LOSS-RESILIENT GENERATIVE CODEC FOR VIDEO CONFERENCING
Tianhong Li ⋅ Vibhaalakshmi Sivaraman ⋅ Pantea Karimi ⋅ Lijie Fan ⋅ Mohammad Alizadeh ⋅ Dina Katabi
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
Tiyasa Mitra ⋅ Ritika Borkar ⋅ Nidhi Bhatia ⋅ Shivam Raj ⋅ hongkuan zhou ⋅ Yan Ru Pei ⋅ Vishwanath Venkatesan ⋅ Kyle Kranen ⋅ Ramon Matas ⋅ Dheevatsa Mudigere ⋅ Ritchie Zhao ⋅ Maximilian Golub ⋅ Arpan Dutta ⋅ Suresh Nambi ⋅ Sailaja Madduri ⋅ Dharmesh Jani ⋅ Brian Pharris ⋅ Itay Neeman ⋅ Bita Darvish Rouhani
Rethinking DVFS for Mobile LLMs: Unified Energy-Aware Scheduling with CORE
Zongpu Zhang ⋅ Pranab Dash ⋅ Qiang Xu ⋅ Y. Charlie Hu ⋅ Jian Li ⋅ Haibing Guan
Optimizing Deployment Configurations for LLM Inference
Sungmin Cho ⋅ Jaewon Lee ⋅ Chunqiang Tang ⋅ Yejin Lee ⋅ Geonhwa Jeong ⋅ Anca Agape ⋅ Scott Batura ⋅ Vincent Boivin ⋅ Stephen Chen ⋅ Renfei Chen ⋅ Sijia Chen ⋅ Yan Cui ⋅ Bradley Davis ⋅ Summer Deng ⋅ Nick Egebo ⋅ Emad El-Haraty ⋅ Sebastien Estienne ⋅ Lu Fang ⋅ Lu Fang ⋅ Joshua Fromm ⋅ Raj Ganapathy ⋅ Vedanuj Goswami ⋅ Liangpeng Guo ⋅ Ye Hu ⋅ Chenheli Hua ⋅ Jianyu Huang ⋅ Aya Ibrahim ⋅ Niranjan Jagannath ⋅ Hongyi Jia ⋅ Changkyu Kim ⋅ Shikai Li ⋅ Brandon Liu ⋅ Jiawen Liu ⋅ Ajit Mathews ⋅ Xiaozhu Meng ⋅ Vlad Tiberiu Mihailescu ⋅ Amit Nagpal ⋅ Maxim Naumov ⋅ Michal Ostrowski ⋅ Jialin Ouyang ⋅ Jason Park ⋅ Sarunya Pumma ⋅ Ye Qi ⋅ Zixi Qi ⋅ Jeremy Francis Reizenstein ⋅ Rajasi Saha ⋅ Nandhini Santhanam ⋅ Zhan Shu ⋅ Ruan Silva ⋅ Grigory Sizov ⋅ Jon Swenson ⋅ Brandon Taylor ⋅ Chris Thi ⋅ Adolfo Victoria ⋅ Yunfan Wang ⋅ Pengchao Wang ⋅ Wenchen Wang ⋅ Xiaodong Wang ⋅ Bram Wasti ⋅ Wei Xu ⋅ Qirui Yang ⋅ Jingyi Yang ⋅ Hector Yuen ⋅ Zhengyuan Zhang ⋅ Jing Zhang ⋅ Yi Zhen ⋅ Yanjun Zhou
EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence
Ansel Erol ⋅ Seungjun Lee ⋅ Divya Mahajan
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
Nicholas Santavas ⋅ Kareem Eissa ⋅ Patrycja Cieplicka ⋅ Piotr Florek ⋅ Matteo Nulli ⋅ Stefan Vasilev ⋅ Seyyed Hashemi ⋅ Antonios Gasteratos ⋅ Shahram Khadivi
Scaling Up Large Language Models Serving Systems for Semantic Job Search
Kayhan Behdin ⋅ Qingquan Song ⋅ Sriram Vasudevan ⋅ Jian Sheng ⋅ Xiaojing Ma ⋅ Zhengze Zhou ⋅ Chuanrui Zhu ⋅ Guoyao Li ⋅ Chanh Nguyen ⋅ Sayan Ghosh ⋅ Hejian Sang ⋅ Ata Fatahi ⋅ Sundara Ramachandran ⋅ Xiaoqing Wang ⋅ Qing Lan ⋅ Vinay S ⋅ Qi Guo ⋅ Caleb Johnson ⋅ Zhipeng Wang ⋅ Fedor Borisyuk
Sparing Strategies to Minimize Reliability Impact On Large Training Jobs
Kevin Quirk ⋅ Matthew Lennie ⋅ Ehsan K. Ardestani ⋅ Satyajeet Ahuja ⋅ Matthew Bergeron ⋅ Andrew Grier ⋅ Zhaodong Wang ⋅ Mustafa Ozdal ⋅ Xu Zhang ⋅ Abhinav Triguna ⋅ Ying Zhang ⋅ Mathew Oldham ⋅ Chunqiang Tang
Massive-Scale Out-Of-Core UMAP on the GPU
Jinsol Park ⋅ Corey Nolet ⋅ Edward Raff ⋅ Tim Oates ⋅ Akira Naruse
Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference
Mengtian Yang ⋅ Zhekun Zhang ⋅ Mingheng Wu ⋅ jianwen yan ⋅ Hanshi Sun ⋅ Li-Wen Chang
veScale-FSDP: Flexible and High-Performance FSDP at Scale
Zezhou Wang ⋅ Youjie Li ⋅ Zhiqi Lin ⋅ Jiacheng Yang ⋅ Cong Xie ⋅ Guanyu Feng ⋅ ZHENG ZHONG ⋅ Ziyue Huang ⋅ Hongyu Zhu ⋅ Zhi Zhang ⋅ Yanghua Peng ⋅ Xin Liu
AXLearn: Modular, Hardware-Agnostic Large Model Training
Mark Lee ⋅ Chang Lan ⋅ Tom Gunter ⋅ John Peebles ⋅ Hanzhi Zhou ⋅ Xuan Zou ⋅ Sneha Bangalore ⋅ Chung-Cheng Chiu ⋅ Nan Du ⋅ Xianzhi Du ⋅ Philipp Dufter ⋅ Liang He ⋅ Ruixuan Hou ⋅ Haoshuo Huang ⋅ Dongseong Hwang ⋅ Xiang Kong ⋅ Jinhao Lei ⋅ Tao Lei ⋅ Meng Li ⋅ Li Li ⋅ Jiarui Lu ⋅ Zhiyun Lu ⋅ Yiping Ma ⋅ David Qiu ⋅ Vivek Rathod ⋅ Senyu Tong ⋅ Zhucheng Tu ⋅ Chong Wang ⋅ Jianyu Wang ⋅ Yongqiang Wang ⋅ Zirui Wang ⋅ Floris Weers ⋅ Sam Wiseman ⋅ Guoli Yin ⋅ Bowen Zhang ⋅ Xiyou Zhou ⋅ Danyang Zhuo ⋅ Cheng Leong ⋅ Ruoming Pang
Hawkeye: Reproducing GPU-Level Non-Determinism
Erez Badash ⋅ Dan Boneh ⋅ Ilan Komargodski ⋅ Megha Srivastava
GUARD: SCALABLE STRAGGLER DETECTION AND NODE HEALTH MANAGEMENT FOR LARGE-SCALE TRAINING
guanliang liu ⋅ Abhinandan Patni ⋅ congzhu lin ⋅ Zoe Zeng ⋅ Jack Wittmayer ⋅ Yinghong Liu ⋅ josh wu ⋅ Anthony Ko ⋅ Alexander Zhipa ⋅ Ashvin Nihalani ⋅ Binxuan Huang ⋅ Cong Cheng ⋅ Mi Sun ⋅ Vijay rajakumar ⋅ Rejith Joseph ⋅ Parthasarathy Govindarajen
DriftBench: Measuring and Predicting Infrastructure Drift in LLM Serving Systems
Gianluigi Vitale
MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs
Jiyuan Zhang ⋅ Yining Liu ⋅ Siqi Yan ⋅ Lisen Deng ⋅ Jennifer Cao ⋅ Shuqi Yang ⋅ Bi Xue ⋅ Min Ni ⋅ Shen Li
PARROT: Persuasion and Agreement Robustness Rating of Output Truth — A Sycophancy Robustness Benchmark for LLMs
Özay Ezerceli ⋅ Mahmoud ElHussieni
FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost
Chenhao Feng ⋅ Haoli Zhang ⋅ Shakhzod Ali-zade ⋅ Yanli Zhao ⋅ Liang Luo ⋅ Jennifer Cao ⋅ Lisen Deng ⋅ Siqiao Chen ⋅ Chenyu Zhao ⋅ Tristan Rice ⋅ Daniel Johnson ⋅ Min Si ⋅ Tiantu Xu ⋅ Yi Zhang ⋅ Evgenii Kolpakov ⋅ Siqi Yan ⋅ Chuanhao Zhuge ⋅ Min Ni ⋅ Bi Xue ⋅ Qunshu Zhang ⋅ Shen Li
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
Stuart H. Sul ⋅ Simran Arora ⋅ Benjamin Spector ⋅ Christopher Ré
XProf: An Open, Scalable, and Extensible Profiling System for the Modern ML Stack
Robert Hundt ⋅ Naveen Kumar ⋅ Jose Baiocchi Paredes ⋅ Scott Goodson ⋅ Clive Verghese ⋅ Prasanna Rengasamy ⋅ Kelvin Le ⋅ Jiya Zhang ⋅ Charles Alaras ⋅ Yin Zhang ⋅ Kan Cai ⋅ Jiten Thakkar ⋅ Sai Ganesh Bandiatmakuri ⋅ Yogesh SY ⋅ Ani Udipi ⋅ Vikas Agarwal
Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel
Hongyi Jin ⋅ Bohan Hou ⋅ Guanjie Wang ⋅ Ruihang Lai ⋅ Jinqi Chen ⋅ Zihao Ye ⋅ Yaxing Cai ⋅ Yixin Dong ⋅ Xinhao Cheng ⋅ Zhihao Zhang ⋅ Yilong Zhao ⋅ Yingyi Huang ⋅ Lijie Yang ⋅ Jinchen Jiang ⋅ Gabriele Oliaro ⋅ Jianan Ji ⋅ Xupeng Miao ⋅ Vinod Grover ⋅ Todd Mowry ⋅ Zhihao Jia ⋅ Tianqi Chen
AIRS: Scaling Live Inference in Resource Constrained Environments
Nilesh Jagnik ⋅ Xiaohao Yang ⋅ Tuan Do ⋅ Chelsea Chen ⋅ Harshvardhan GM
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang ⋅ Shaowei Zhu ⋅ Anjiang Wei ⋅ Zhenyu Song ⋅ Allen Nie ⋅ Zhen Jia ⋅ Nandita Vijaykumar ⋅ Yida Wang ⋅ Kunle Olukotun
SAKURAONE: An Open Ethernet–Based AI HPC System and Its Observed Workload Dynamics in a Single-Tenant LLM Development Environment
Fumikazu KONISHI ⋅ Yuuki Tsubouchi ⋅ Hirofumi Tsuruta
DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling
Yi Pan ⋅ Yile Gu ⋅ Luo Jinbin ⋅ Yibo Wu ⋅ Ziren Wang ⋅ Hongtao Zhang ⋅ Ziyi Xu ⋅ Shengkai Lin ⋅ Baris Kasikci ⋅ Stephanie Wang
MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
Srinivas ⋅ Andrey Balogh ⋅ Brad B ⋅ Brian Coutinho ⋅ Louis Feng ⋅ Sheng Fu ⋅ Sanshan Gao ⋅ Mehryar Garakani ⋅ Taekyung Heo ⋅ David Kanter ⋅ Josh Ladd ⋅ Ziwei Li ⋅ Winston Liu ⋅ Changhai Man ⋅ Dan Mihailescu ⋅ Spandan More ⋅ Joongun Park ⋅ Ashwin Ramachandran ⋅ Vinay Ramakrishnaiah ⋅ Saeed Rashidi ⋅ Vijay Janapa Reddi ⋅ Puneet Sharma ⋅ Phio Tian ⋅ William Won ⋅ Hanjiang Wu ⋅ Huan Xu ⋅ Jinsun Yoo ⋅ Tushar Krishna
ApproxMLIR : Accuracy-Aware Compiler for Compound ML System
Hao Ren ⋅ Yi Mu ⋅ Sasa Misailovic
ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler
Bohua Zou ⋅ Debayan Roy ⋅ Dhimankumar Airao ⋅ Weihao Xu ⋅ Binqi Sun ⋅ Yutao Liu ⋅ Haibo Chen
HipKittens: Fast and Furious AMD Kernels
William Hu ⋅ Drew Wadsworth ⋅ Sean Siddens ⋅ Stanley Winata ⋅ Daniel Fu ⋅ Ryan Swann ⋅ Muhammad Osama ⋅ Christopher Ré ⋅ Simran Arora
Machine Learning Fleet Efficiency: Improving TPU Systems at Scale with ML Productivity Goodput
Arissa Wongpanich ⋅ Tayo Oguntebi ⋅ Jose Baiocchi Paredes ⋅ Yu Wang ⋅ Phitchaya Phothilimthana ⋅ Ritwika Mitra ⋅ Zongwei Zhou ⋅ Naveen Kumar ⋅ Vijay Janapa Reddi
Dataflow Is All You Need
Darshan Gandhi ⋅ Pushkar Nandkar ⋅ David Koeplinger ⋅ Nasim Farahini ⋅ Romy Tsoupidi ⋅ Samuel Rydh ⋅ Matheen Musaddiq ⋅ Tuowen Zhao ⋅ Reid Goodbar ⋅ Nathan Sheeley ⋅ Leon Zhang ⋅ Matthew Shaffer ⋅ John Long ⋅ Han Wang ⋅ Angela Wang ⋅ Arjun Sabnis ⋅ Joshua Brot ⋅ Yun Du ⋅ Håkan Zeffer ⋅ Mingran Wang ⋅ Raghu Prabhakar
Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks
Dionysios Adamopoulos ⋅ Anastasia Poulopoulou ⋅ Georgios Goumas ⋅ Christina Giannoula
Efficient, VRAM-Constrained xLM Inference on Clients
Aditya Ukarande ⋅ Deep Shekhar ⋅ Marc Blackstein ⋅ Ram Rangan
Attribution-based Sparse Activation in Large Language Models
Jifeng Song ⋅ Xiangyu Yin ⋅ Boyuan Yang ⋅ Kai Huang ⋅ Weichen Liu ⋅ Wei Gao
Wave: A Symbolic Python DSL And Compiler for High-Performance Machine Learning
Harsh Menon ⋅ Oleksandr Zinenko ⋅ Gaurav Verma ⋅ Stanley Winata ⋅ Ivan Butygin ⋅ Nithin Meganathan ⋅ Sanket Pandit ⋅ William Gallard Hatch ⋅ Surya Jasper ⋅ Megan Kuo ⋅ Sahil FAIZAL ⋅ Ashay Rane ⋅ Aurore De Spirlet ⋅ Martin P. Lücke
Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants
Bozhi You ⋅ Irene Wang ⋅ Zelal Mustafaoglu ⋅ Abhinav Jangda ⋅ Angélica Moreira ⋅ Roshan Dathathri ⋅ Divya Mahajan ⋅ Keshav Pingali
CATWILD: Compiler Autotuning for TPU workloads in the Wild
Ignacio Cano ⋅ Yu Wang ⋅ Mike Burrows ⋅ Ziqiang Feng ⋅ Matheus Camargo ⋅ Chao Wang ⋅ David Liu ⋅ Tengyu Sun ⋅ Alexander Wertheim ⋅ Arissa Wongpanich ⋅ Christof Angermueller ⋅ Hyojun Kim ⋅ Wenqi Cao ⋅ Aleksey Orekhov ⋅ Amit Sabne ⋅ Emma Sevastian ⋅ Mehrdad Khani ⋅ Karthik Murthy ⋅ Berkin Ilbeyi ⋅ Subhankar Shah ⋅ Ryan Lefever ⋅ Arjun Khare ⋅ Ankit Sinha ⋅ Peter Ma ⋅ Matt Bierbaum ⋅ Jeremiah Wilke ⋅ Emily Donahue ⋅ Sami Abu-El-Haija ⋅ Nikhil Sarda ⋅ Vineetha Govindaraj ⋅ Shobha Vasudevan ⋅ Kirill Gugaev ⋅ Idan Nachman ⋅ Jie Sun ⋅ Jose Baiocchi Paredes ⋅ Samrat Ghosh ⋅ Domagoj Babic ⋅ Zongwei Zhou ⋅ Naveen Kumar ⋅ Phitchaya Phothilimthana
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
Ted Zadouri ⋅ Markus Hoehnerbach ⋅ Jay Shah ⋅ Vijay Thakkar ⋅ Tri Dao
Go to Event Page