Calendar

Seminar

Jun 7, 2024

MuxServe: Flexible Multiplexing for Efficient Multiple LLM Serving LLM Co-Serving

Duan Jiangfei: Video

May 9, 2024

Zero Bubble (Almost) Pipeline Parallelism (ICLR’24) Pipeline Parallelism

Wan Xinyi: Video

Apr 16, 2024

Centauri: Enabling Efficient Scheduling for Communication-Computation Overlap in Large Model Training via Communication Partitioning (ASPLOS’24 Best Paper) Model Parallelism

Chen Chang: Video

Apr 5, 2024

DeltaZip: Multi-Tenant Language Model Serving via Delta Compression LLM Co-Serving

Yao Xiaozhe: Video

Feb 2, 2024

AMSP: Super-Scaling LLM Training via Advanced Model States Partitioning Model Parallelism

Chen Qiaoling: Video

Jan 12, 2024

1 year after ChatGPT, where do the best open source LLMs stand? LLM

Mathieu Ravaut: Video

Nov 10, 2023

Automatic Root Cause Analysis via Large Language Models for Cloud Incidents(EuroSys’24) LLM for Coding

Chen Yinfang: Video

Oct 20, 2023

EasyScale: Elastic Training with Consistent Accuracy and Improved Utilization on GPUs (SC’23) Elastic Training

Li Mingzhen: Video

Sep 29, 2023

Fast LLM Serving with vLLM and PagedAttention (SOSP’23) LLM Serving

Li Zhuohan: Video

Sep 15, 2023

bbTopk: Bandwidth-Aware Sparse Allreduce with Blocked Sparsification for Efficient Distributed Training (ICDCS’23) Coll. Comm

Chen Chang: Video

Jul 28, 2023

Hanayo: Harnessing Wave-Like Pipeline Parallelism for Enhanced Large Model Training Efficiency (SC’23) Pipeline Parallelism

Liu Ziming: Video

Jun 16, 2023

FedTree: FedTree: A Federated Learning System For Trees (MLSys’23) Fed-Learning

Li Qinbin: Video

Jun 13, 2023

Optimizing Dynamic Neural Networks with Brainstorm (OSDI’23) Compiler

Cui Weihao: Video

May 26, 2023

Long Sequence Training from System Perspective (ACL’23) LLM

Xue Fuzhao: Video

Apr 28, 2023

Lucid: A Non-intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs（ASPLOS’23 Best Paper) Scheduler

Hu Qinghao: Video

Apr 14, 2023

Round Table Introduction Panel

Shi Ziji: No Video