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
BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models
Zhengyang Wang ⋅ Ziyue Liu ⋅ Ruijie Zhang ⋅ Avinash Maurya ⋅ ⋅ Paul Hovland ⋅ ⋅ zheng Zhang
Efficient Long-Context Language Model Training by Core Attention Disaggregation
Yonghao Zhuang ⋅ Junda Chen ⋅ ⋅ Yi Gu ⋅ Yibo Zhu ⋅ Yimin Jiang ⋅ Ion Stoica ⋅ Hao Zhang ⋅ Eric Xing
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
Wenxuan Li ⋅ Chengruidong Zhang ⋅ Huiqiang Jiang ⋅ Yucheng Li ⋅ ⋅ Lili Qiu
NEST: Network- and Memory-Aware Device Placement for Distributed Deep Learning
Irene Wang ⋅ ⋅ Arvind Krishnamurthy ⋅ Divya Mahajan
ProTrain: Efficient LLM Training via Automatic Memory Management
Hanmei Yang ⋅ ⋅ Yao Fu ⋅ ⋅ Ramine Roane ⋅ Hui Guan ⋅ Tongping Liu
Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP
Yilong Zhao ⋅ Xiaonan Nie ⋅ Kan Zhu ⋅ ⋅ ⋅ Hongxiang Hao ⋅ Yang Zhou ⋅ Baris Kasikci ⋅ Ion Stoica
Go to Event Page
Oral
8:30 AM - 10:00 AM
6 Events in this session
BEAM: Joint Resource–Power Optimization for Energy-Efficient LLM Inference under SLO contraints
Hyunjae Lee ⋅ Sangjin Choi ⋅ Seungjae Lim ⋅ Youngjin Kwon
BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization
YOUHE JIANG ⋅ Fangcheng Fu ⋅ Eiko Yoneki
Breaking the Ice: Analyzing Cold Start Latency in vLLM
Huzaifa Shaaban Kabakibo ⋅ Animesh Trivedi ⋅ Lin Wang
FaaScale: Unlocking Fast LLM Scaling for Serverless Inference
Minchen Yu ⋅ Rui Yang ⋅ ⋅ Zhaoyuan Su ⋅ Sheng Yao ⋅ Tingfeng Lan ⋅ ⋅ Zirui Wang ⋅ Yue Cheng ⋅ Wei Wang ⋅ ⋅ Ruichuan Chen
Locality-Aware Beam Scheduling for Efficient Test-Time Compute with a Consumer-grade GPU
Hsing-Ti Wang ⋅ Hung-Tso Shiao ⋅ Chia-Lin Yang
MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing
Zhaoyuan Su ⋅ Zeyu Zhang ⋅ Tingfeng Lan ⋅ Zirui Wang ⋅ ⋅ Juncheng Yang ⋅ Yue Cheng
Go to Event Page
Invited Talk

Keynote - Amin Vahdat

Amin Vahdat
10:30 AM - 11:30 AM
Speaker Bio
Amin Vahdat
Amin Vahdat is a Fellow and Chief Technologist for AI Infrastructure at Google, where his team is responsible for delivering industry-leading infrastructure which spans custom silicon, data centers, network, and supply chain and operations. This infrastructure serves Alphabet, Google and the world, and Artificial Intelligence technologies that empower ML developers and solve customers’ most pressing business challenges. In the past, he was Vice President and General Manager for Google's compute, storage, and network hardware and software infrastructure. Until 2019, he was the Technical Lead and Vice President for the Networking organization at Google.
... more
Session
10:30 AM - 11:30 AM
Oral
1:00 PM - 2:30 PM
6 Events in this session
Automated Algorithm Design for Auto-Tuning Optimizers
Floris-Jan Willemsen ⋅ Niki van Stein ⋅ Ben van Werkhoven
LLMInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
Shanli Xing ⋅ Vivian Zhai ⋅ Alexander Jiang ⋅ Yixin Dong ⋅ Yong Wu ⋅ Zihao Ye ⋅ ⋅ Yingyi Huang ⋅ Yineng Zhang ⋅ ⋅ ⋅ Luis Ceze ⋅ Tianqi Chen
Practical Adversarial Multi-Armed Bandits with Sublinear Runtime
Kasper Overgaard Mortensen ⋅ Ama Bembua Bainson ⋅ ⋅ Kristoffer Strube ⋅ Renata Borovica-Gajic ⋅ Andrea Paudice ⋅ Davide Mottin ⋅ Panagiotis Karras
Unified LLM Model for Power, Performance, and Area Prediction from Hardware Code
Armin Abdollahi ⋅ Mehdi Kamal ⋅ Massoud Pedram
Virtual Machine NUMA Placement at Scale: Learning the Norm, Shielding the Tail
Yibo Zhao ⋅ Tianyuan Wu ⋅ HUI XUE ⋅ Qi Chen ⋅ Zhenhua Han ⋅ ⋅ ⋅ ⋅ ⋅ Jui-Hao Chiang ⋅ Mingxia Li ⋅ Yuqing Yang ⋅ Cheng Tan ⋅ Fan Yang ⋅ Peng Cheng ⋅ Yongqiang Xiong ⋅ Lili Qiu ⋅ Lidong Zhou
When Machine Learning Isn’t Sure: Building Resilient ML-Based Computer Systems by Embracing Uncertainty
Varun Gohil ⋅ Nevena Stojkovic ⋅ Noman Bashir ⋅ ⋅ Gaurang Upasani ⋅ David Lo ⋅ Parthasarathy Ranganathan ⋅ Christina Delimitrou
Go to Event Page
Oral
1:00 PM - 2:30 PM
6 Events in this session
FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management
Nazmul Takbir ⋅ Hamidreza Koshkak ⋅ Nikil Dutt ⋅ Sangeetha Abdu Jyothi
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia ⋅ Xiaoxia Wu ⋅ Jisen Li ⋅ Tsai-chuan Wu ⋅ Junxiong Wang ⋅ Jue Wang ⋅ Chenxi Li ⋅ Aman Singhal ⋅ Alay Dilipbhai Shah ⋅ ⋅ Donglin Zhuang ⋅ Zhongzhu Zhou ⋅ Ben Athiwaratkun ⋅ Zhen Zheng ⋅ Shuaiwen Song
MAC-Attention: a Match--Amend--Complete scheme for fast and accurate attention computation
Jinghan Yao ⋅ Sam Jacobs ⋅ Walid Krichene ⋅ Masahiro Tanaka ⋅ Dhabaleswar Panda
OPKV: A High-Throughput Plugin-Driven Framework for Recallable Sparsity in Paged KV Cache Systems
Huazheng Lao ⋅ Xiaofeng Li ⋅ Rui Xu ⋅ Long Chen ⋅ Xia Zhu ⋅
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
Jiayi Tian ⋅ Seyedarmin Azizi ⋅ Yequan Zhao ⋅ Erfan Potraghloo ⋅ Sean McPherson ⋅ Sharath Nittur Sridhar ⋅ Zhengyang Wang ⋅ zheng Zhang ⋅ Massoud Pedram ⋅ Souvik Kundu
Using Span Queries to Optimize Cache and Attention Locality
Paul Castro ⋅ Nick Mitchell ⋅ Nathan Ordonez ⋅ Thomas Parnell ⋅ Mudhakar Srivatsa ⋅ Antoni Viros i Martin
Go to Event Page
Oral
2:45 PM - 4:15 PM
6 Events in this session
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
Zelei Shao ⋅ Vikranth Srivatsa ⋅ Junxiong Wang ⋅ Chenfeng Xu ⋅ Xiaoxia Wu ⋅ ⋅ ⋅ Qingyang Wu ⋅ Jue Wang ⋅ Ameen Patel ⋅ Yiying Zhang ⋅ Percy Liang ⋅ Tri Dao ⋅ Ben Athiwaratkun ⋅ Ce Zhang
FlexTrain: Scalable Hybrid-Parallel Training with Elastic Resource Utilization and Consistent Accuracy
Weilin Cai ⋅ Diandian Gu ⋅ Jun Wang ⋅ ⋅ Jiayi Huang
HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments
Yongjun He ⋅ Shuai Zhang ⋅ ⋅ Xiyuan Zhang ⋅ Boran Han ⋅ Bernie Wang ⋅ Huzefa Rangwala ⋅ George Karypis
Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Justin Bauer ⋅ Thomas Walshe ⋅ Derek Pham ⋅ Harit Vishwakarma ⋅ Armin Parchami ⋅ Frederic Sala ⋅ Paroma Varma
NexSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
qiaoling chen ⋅ Zijun Liu ⋅ Peng Sun ⋅ Shenggui Li ⋅ Guoteng Wang ⋅ Ziming Liu ⋅ Yonggang Wen ⋅ Siyuan Feng ⋅ Tianwei Zhang
Pylo: Towards Accessible Learned Optimizers in PyTorch
Paul Janson ⋅ Benjamin Thérien ⋅ Quentin Anthony ⋅ Xiaolong Huang ⋅ Abhinav Moudgil ⋅ Eugene Belilovsky
Go to Event Page
Oral
2:45 PM - 4:15 PM
6 Events in this session
CRAFT: Cost-aware Expert Replica Allocation with Fine-Grained Layerwise Estimations
Adrian Zhao ⋅ ⋅ ⋅ Lingfan Yu ⋅ Haozheng Fan ⋅ Jun Wu ⋅ Yida Wang ⋅ Nandita Vijaykumar
Demystifying the Mixture of Experts Serving Tax
Pratyush Patel ⋅ Arvind Krishnamurthy
FarSkip-Collectives: Unhobbling Blocking Communication in Mixture of Experts Models
Yonatan Dukler ⋅ ⋅ ⋅ Vikram Appia ⋅ Emad Barsoum
FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error
Fengjuan Wang ⋅ Zhiyi Su ⋅ ⋅ ⋅ Sun Mou
GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving
Shakya Jayakody ⋅ Youpeng Zhao ⋅ Chinmay Dhanraj Nehate ⋅ Jun Wang
RaidServe: High-performance Resilient Serving
Ziyi Xu ⋅ Zhiqiang Xie ⋅ Swapnil Gandhi ⋅ Christos Kozyrakis
Go to Event Page
Oral
4:30 PM - 6:00 PM
5 Events in this session
CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
Soroush Tabesh ⋅ ⋅ Andrei Panferov ⋅ ⋅
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
Zhen Zheng ⋅ Xiaonan Song ⋅ Chuanjie Liu
Once-for-All Channel Mixers (HyperTinyPW): Generative Compression for TinyML
Search Your NVFP4 Scales!
Tanmaey Gupta ⋅ Hayden Prairie ⋅ Xiaoxia Wu ⋅ Reyna Abhyankar ⋅ Qingyang Wu ⋅ Austin Silveria ⋅ Pragaash Ponnusamy ⋅ Jue Wang ⋅ Ben Athiwaratkun ⋅ Shuaiwen Song ⋅ Tri Dao ⋅ Daniel Fu ⋅ Christopher De Sa
Shannonic: Efficient Entropy-Optimal Compression for ML Workloads
Kareem Ibrahim ⋅ ⋅ Andreas Moshovos
Go to Event Page
Oral
4:30 PM - 6:00 PM
6 Events in this session
A Lightweight High-Throughput Collective-Capable NoC for Large-Scale ML Accelerators
Luca Colagrande ⋅ Lorenzo Leone ⋅ Chen Wu ⋅ ⋅ ⋅ Luca Benini
DreamDDP: Accelerating Low-Bandwidth Geo-Distributed LLM Training with Layer-wise Partial Synchronization
Zhenheng Tang ⋅ Zichen TANG ⋅ Junlin Huang ⋅ Xinglin Pan ⋅ Rudan Yan ⋅ Yuxin Wang ⋅ ⋅ Shaohuai Shi ⋅ Xiaowen Chu ⋅
GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading
Jaeyong Song ⋅ Seongyeon Park ⋅ Hongsun Jang ⋅ Jaewon Jung ⋅ Hunseong Lim ⋅ Junguk Hong ⋅ Jinho Lee
Grolar: Efficient LLM Training on Heterogeneous Clusters
Runsheng Guo ⋅ Utkarsh Anand ⋅ Khuzaima Daudjee ⋅ Rathijit Sen
HexiScale: Facilitating Large Language Model Training over Heterogeneous Hardware
Ran Yan ⋅ YOUHE JIANG ⋅ Xiaonan Nie ⋅ Fangcheng Fu ⋅ Bin CUI ⋅ Binhang Yuan
RDMA Point-to-Point Communication for LLM Systems
Nandor Licker ⋅ Kevin Hu ⋅ Vladimir Zaytsev ⋅ Lequn Chen
Go to Event Page
Poster
6:00 PM - 8:00 PM
47 Events in this session
A Lightweight High-Throughput Collective-Capable NoC for Large-Scale ML Accelerators
Luca Colagrande ⋅ Lorenzo Leone ⋅ Chen Wu ⋅ ⋅ ⋅ Luca Benini
Automated Algorithm Design for Auto-Tuning Optimizers
Floris-Jan Willemsen ⋅ Niki van Stein ⋅ Ben van Werkhoven
BEAM: Joint Resource–Power Optimization for Energy-Efficient LLM Inference under SLO contraints
Hyunjae Lee ⋅ Sangjin Choi ⋅ Seungjae Lim ⋅ Youngjin Kwon
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
Zelei Shao ⋅ Vikranth Srivatsa ⋅ Junxiong Wang ⋅ Chenfeng Xu ⋅ Xiaoxia Wu ⋅ ⋅ ⋅ Qingyang Wu ⋅ Jue Wang ⋅ Ameen Patel ⋅ Yiying Zhang ⋅ Percy Liang ⋅ Tri Dao ⋅ Ben Athiwaratkun ⋅ Ce Zhang
BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models
Zhengyang Wang ⋅ Ziyue Liu ⋅ Ruijie Zhang ⋅ Avinash Maurya ⋅ ⋅ Paul Hovland ⋅ ⋅ zheng Zhang
BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization
YOUHE JIANG ⋅ Fangcheng Fu ⋅ Eiko Yoneki
Breaking the Ice: Analyzing Cold Start Latency in vLLM
Huzaifa Shaaban Kabakibo ⋅ Animesh Trivedi ⋅ Lin Wang
CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
Soroush Tabesh ⋅ ⋅ Andrei Panferov ⋅ ⋅
CRAFT: Cost-aware Expert Replica Allocation with Fine-Grained Layerwise Estimations
Adrian Zhao ⋅ ⋅ ⋅ Lingfan Yu ⋅ Haozheng Fan ⋅ Jun Wu ⋅ Yida Wang ⋅ Nandita Vijaykumar
Demystifying the Mixture of Experts Serving Tax
Pratyush Patel ⋅ Arvind Krishnamurthy
DreamDDP: Accelerating Low-Bandwidth Geo-Distributed LLM Training with Layer-wise Partial Synchronization
Zhenheng Tang ⋅ Zichen TANG ⋅ Junlin Huang ⋅ Xinglin Pan ⋅ Rudan Yan ⋅ Yuxin Wang ⋅ ⋅ Shaohuai Shi ⋅ Xiaowen Chu ⋅
Efficient Long-Context Language Model Training by Core Attention Disaggregation
Yonghao Zhuang ⋅ Junda Chen ⋅ ⋅ Yi Gu ⋅ Yibo Zhu ⋅ Yimin Jiang ⋅ Ion Stoica ⋅ Hao Zhang ⋅ Eric Xing
FaaScale: Unlocking Fast LLM Scaling for Serverless Inference
Minchen Yu ⋅ Rui Yang ⋅ ⋅ Zhaoyuan Su ⋅ Sheng Yao ⋅ Tingfeng Lan ⋅ ⋅ Zirui Wang ⋅ Yue Cheng ⋅ Wei Wang ⋅ ⋅ Ruichuan Chen
FarSkip-Collectives: Unhobbling Blocking Communication in Mixture of Experts Models
Yonatan Dukler ⋅ ⋅ ⋅ Vikram Appia ⋅ Emad Barsoum
FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management
Nazmul Takbir ⋅ Hamidreza Koshkak ⋅ Nikil Dutt ⋅ Sangeetha Abdu Jyothi
FlexTrain: Scalable Hybrid-Parallel Training with Elastic Resource Utilization and Consistent Accuracy
Weilin Cai ⋅ Diandian Gu ⋅ Jun Wang ⋅ ⋅ Jiayi Huang
FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error
Fengjuan Wang ⋅ Zhiyi Su ⋅ ⋅ ⋅ Sun Mou
GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving
Shakya Jayakody ⋅ Youpeng Zhao ⋅ Chinmay Dhanraj Nehate ⋅ Jun Wang
GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading
Jaeyong Song ⋅ Seongyeon Park ⋅ Hongsun Jang ⋅ Jaewon Jung ⋅ Hunseong Lim ⋅ Junguk Hong ⋅ Jinho Lee
Grolar: Efficient LLM Training on Heterogeneous Clusters
Runsheng Guo ⋅ Utkarsh Anand ⋅ Khuzaima Daudjee ⋅ Rathijit Sen
HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments
Yongjun He ⋅ Shuai Zhang ⋅ ⋅ Xiyuan Zhang ⋅ Boran Han ⋅ Bernie Wang ⋅ Huzefa Rangwala ⋅ George Karypis
HexiScale: Facilitating Large Language Model Training over Heterogeneous Hardware
Ran Yan ⋅ YOUHE JIANG ⋅ Xiaonan Nie ⋅ Fangcheng Fu ⋅ Bin CUI ⋅ Binhang Yuan
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia ⋅ Xiaoxia Wu ⋅ Jisen Li ⋅ Tsai-chuan Wu ⋅ Junxiong Wang ⋅ Jue Wang ⋅ Chenxi Li ⋅ Aman Singhal ⋅ Alay Dilipbhai Shah ⋅ ⋅ Donglin Zhuang ⋅ Zhongzhu Zhou ⋅ Ben Athiwaratkun ⋅ Zhen Zheng ⋅ Shuaiwen Song
Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Justin Bauer ⋅ Thomas Walshe ⋅ Derek Pham ⋅ Harit Vishwakarma ⋅ Armin Parchami ⋅ Frederic Sala ⋅ Paroma Varma
LLMInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
Shanli Xing ⋅ Vivian Zhai ⋅ Alexander Jiang ⋅ Yixin Dong ⋅ Yong Wu ⋅ Zihao Ye ⋅ ⋅ Yingyi Huang ⋅ Yineng Zhang ⋅ ⋅ ⋅ Luis Ceze ⋅ Tianqi Chen
Locality-Aware Beam Scheduling for Efficient Test-Time Compute with a Consumer-grade GPU
Hsing-Ti Wang ⋅ Hung-Tso Shiao ⋅ Chia-Lin Yang
MAC-Attention: a Match--Amend--Complete scheme for fast and accurate attention computation
Jinghan Yao ⋅ Sam Jacobs ⋅ Walid Krichene ⋅ Masahiro Tanaka ⋅ Dhabaleswar Panda
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
Zhen Zheng ⋅ Xiaonan Song ⋅ Chuanjie Liu
MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing
Zhaoyuan Su ⋅ Zeyu Zhang ⋅ Tingfeng Lan ⋅ Zirui Wang ⋅ ⋅ Juncheng Yang ⋅ Yue Cheng
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
Wenxuan Li ⋅ Chengruidong Zhang ⋅ Huiqiang Jiang ⋅ Yucheng Li ⋅ ⋅ Lili Qiu
NEST: Network- and Memory-Aware Device Placement for Distributed Deep Learning
Irene Wang ⋅ ⋅ Arvind Krishnamurthy ⋅ Divya Mahajan
NexSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
qiaoling chen ⋅ Zijun Liu ⋅ Peng Sun ⋅ Shenggui Li ⋅ Guoteng Wang ⋅ Ziming Liu ⋅ Yonggang Wen ⋅ Siyuan Feng ⋅ Tianwei Zhang
Once-for-All Channel Mixers (HyperTinyPW): Generative Compression for TinyML
OPKV: A High-Throughput Plugin-Driven Framework for Recallable Sparsity in Paged KV Cache Systems
Huazheng Lao ⋅ Xiaofeng Li ⋅ Rui Xu ⋅ Long Chen ⋅ Xia Zhu ⋅
Practical Adversarial Multi-Armed Bandits with Sublinear Runtime
Kasper Overgaard Mortensen ⋅ Ama Bembua Bainson ⋅ ⋅ Kristoffer Strube ⋅ Renata Borovica-Gajic ⋅ Andrea Paudice ⋅ Davide Mottin ⋅ Panagiotis Karras
ProTrain: Efficient LLM Training via Automatic Memory Management
Hanmei Yang ⋅ ⋅ Yao Fu ⋅ ⋅ Ramine Roane ⋅ Hui Guan ⋅ Tongping Liu
Pylo: Towards Accessible Learned Optimizers in PyTorch
Paul Janson ⋅ Benjamin Thérien ⋅ Quentin Anthony ⋅ Xiaolong Huang ⋅ Abhinav Moudgil ⋅ Eugene Belilovsky
RaidServe: High-performance Resilient Serving
Ziyi Xu ⋅ Zhiqiang Xie ⋅ Swapnil Gandhi ⋅ Christos Kozyrakis
RDMA Point-to-Point Communication for LLM Systems
Nandor Licker ⋅ Kevin Hu ⋅ Vladimir Zaytsev ⋅ Lequn Chen
Search Your NVFP4 Scales!
Tanmaey Gupta ⋅ Hayden Prairie ⋅ Xiaoxia Wu ⋅ Reyna Abhyankar ⋅ Qingyang Wu ⋅ Austin Silveria ⋅ Pragaash Ponnusamy ⋅ Jue Wang ⋅ Ben Athiwaratkun ⋅ Shuaiwen Song ⋅ Tri Dao ⋅ Daniel Fu ⋅ Christopher De Sa
Shannonic: Efficient Entropy-Optimal Compression for ML Workloads
Kareem Ibrahim ⋅ ⋅ Andreas Moshovos
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
Jiayi Tian ⋅ Seyedarmin Azizi ⋅ Yequan Zhao ⋅ Erfan Potraghloo ⋅ Sean McPherson ⋅ Sharath Nittur Sridhar ⋅ Zhengyang Wang ⋅ zheng Zhang ⋅ Massoud Pedram ⋅ Souvik Kundu
Unified LLM Model for Power, Performance, and Area Prediction from Hardware Code
Armin Abdollahi ⋅ Mehdi Kamal ⋅ Massoud Pedram
Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP
Yilong Zhao ⋅ Xiaonan Nie ⋅ Kan Zhu ⋅ ⋅ ⋅ Hongxiang Hao ⋅ Yang Zhou ⋅ Baris Kasikci ⋅ Ion Stoica
Using Span Queries to Optimize Cache and Attention Locality
Paul Castro ⋅ Nick Mitchell ⋅ Nathan Ordonez ⋅ Thomas Parnell ⋅ Mudhakar Srivatsa ⋅ Antoni Viros i Martin
Virtual Machine NUMA Placement at Scale: Learning the Norm, Shielding the Tail
Yibo Zhao ⋅ Tianyuan Wu ⋅ HUI XUE ⋅ Qi Chen ⋅ Zhenhua Han ⋅ ⋅ ⋅ ⋅ ⋅ Jui-Hao Chiang ⋅ Mingxia Li ⋅ Yuqing Yang ⋅ Cheng Tan ⋅ Fan Yang ⋅ Peng Cheng ⋅ Yongqiang Xiong ⋅ Lili Qiu ⋅ Lidong Zhou
When Machine Learning Isn’t Sure: Building Resilient ML-Based Computer Systems by Embracing Uncertainty
Varun Gohil ⋅ Nevena Stojkovic ⋅ Noman Bashir ⋅ ⋅ Gaurang Upasani ⋅ David Lo ⋅ Parthasarathy Ranganathan ⋅ Christina Delimitrou
Go to Event Page