Dynamic Graph Neural Networks (DGNNs) can be really useful in many domains, but they are hard to scale. Our new work shows how to achieve an *order of magnitude* speedup when training DGNNs! Joint work with awesome folks Mingyu Guan and Taesoo Kim! arxiv.org/abs/2501.15348
Serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads. Our new work, Omega, shows how to solve this. Joint work with awesome collaborators @daehyeok_kim, @adityaakella and amazing students! arxiv.org/abs/2501.08547
We are fast approaching the PhD application deadline this cycle (Dec 15 for @GeorgiaTech@gatech_scs, we're hiring so consider us if you're interested in systems!), good luck to all applicants!! #AcademicTwitter
We are fast approaching the PhD application deadline this cycle (Dec 15 for @GeorgiaTech@gatech_scs, we're hiring so consider us if you're interested in systems!), good luck to all applicants!! #AcademicTwitter
It's PhD application season again. I'll be on the look out for motivated students. Located in the vibrant city of Atlanta, @GeorgiaTech@gatech_scs is a top 5 school with an awesome set of people. Apply by Dec 15 and mention my name! scs.gatech.edu/phd-programs
MoEs promise reduced parameter activation, but in practice invoke all experts during batched inference. With my awesome students @vima_gupta, Kartik Sinha & collaborator Ada Gavrilovska, we show how MoEs can fulfill their promise in a workload-agnostic way arxiv.org/abs/2411.08982
Our work on accelerating distributed GNN training leveraging a communication-efficient partition refinement scheme and a better caching strategy has been accepted at @TheOfficialACM#CoNEXT 2024!
Our work on accelerating DNN inference on low-cost edges has been accepted to appear at Eurosys 25! Joint work with TanmoySen and HaiyingShen! @ACM@EuroSysConf#eurosys
Our work on improving inference throughput via per-input adaptation has been accepted to appear at SOSP. Thanks to all the reviewers for their insightful reviews, and special thanks to our champion! Excited to visit Austin in November. #sosp#sosp24
Our work on relieving the fundamental tension in ML serving systems has been accepted to appear at SOSP 24! Congrats to the amazing co-primary authors @dai_yinwei and @ruipeterpan! #sosp#sosp24
Our work on relieving the fundamental tension in ML serving systems has been accepted to appear at SOSP 24! Congrats to the amazing co-primary authors @dai_yinwei and @ruipeterpan! #sosp#sosp24
In an hour, @ShubhaSudipta will present our work on resource optimized ML inference by avoiding GPU interference at @usenix#osdi#osdi24. If you're around, please attend the talk and ask him about our work!
Our work on avoiding GPU interference for achieving resource optimized ML inference has been accepted to appear at #osdi#osdi24! Joint work with awesome folks @ShubhaSudipta and HaiyingShen!
Radhika Niranjan Mysore and I are chairing NSDI'25.
Applications for the NSDI 2025 PC are online!
docs.google.com/forms/d/e/1FAI…
We are especially looking for folks from underrepresented groups or geographic regions, so if you know of someone, encourage them to apply.
#NSDI25
ML serving systems face a fundamental tension between throughput & latency. Our new work aims to relieve this: arxiv.org/abs/2312.05385. Led by the awesome co-primary authors @dai_yinwei@ruipeterpan. Want to work on similar problems? Apply to GeorgiaTech by Dec 15!
Our work on automating query planning for ML will appear at #nsdi#nsdi24! Interested in working on similar awesome projects? I'm recruiting PhD students @gatech_scs! Apply by Dec 15 and mention my name!
35 Followers 145 Followingex Protocol Engineering @Akamai | Undergrad '23 @PESUniversity | Networks, Security, Cloud, C++ | he/him | Guitar and linguistic history | views are my own
425 Followers 376 FollowingPostdoc at UC Berkeley Skylab. Incoming assistant professor at UC Davis CS. ML systems, networked systems. Prev: Harvard CS PhD.
2K Followers 295 FollowingAssistant Professor at UIUC CS | Previously @MSFTResearch @Stanford | Creator of Puffer (400k users) | Illinois Networked Systems + AI Lab.
1K Followers 230 FollowingBreaker, Climber, Researcher, Professor.
Interested in making the internet blazing fast, closing the digital divide, and eliminating pesky internet outages.
2K Followers 411 FollowingGeorgia Tech's School of Computer Science is at the forefront of research in AI Foundations, Comp Arch, Data Systems, PLSE, Networking, Systems, and Theory.
2K Followers 278 FollowingAssistant Professor at GT @gatech_scs | Researcher @vmwareresearch | CS PhD @Stanford | make data analytics more scalable and user friendly
5K Followers 681 FollowingExclusively on Mastodon these days: https://t.co/uq8vRRSnQa
Distributed systems and operating systems. @MSFTResearch @uwsyslab
5K Followers 1 FollowingFaculty jobs in Computer Science worldwide. Mostly automated. Mention/DM openings & we'll retweet. Created by @emilianoucl, now run by @shaddih
4K Followers 189 FollowingTechnologist. Founder & CTO of Cambridge Mobile Telematics. Professor at MIT CSAIL. Mobility, Networks, Sensing, Perception, Systems. Cricket.
124K Followers 497 FollowingPrinceton CS prof. Director @PrincetonCITP. I use X to share my research and commentary on the societal impact of AI.
BOOK: AI Snake Oil. Views mine.
581 Followers 915 FollowingSWE at @Google and Assistant Professor at @CUBoulder. Previously @Meta, @IBMResearch, and @ATTResearch. Interests in cloud, networking, and mobile. he/him/his
2K Followers 248 FollowingComputer systems researcher in the ETOS group (https://t.co/hqizZy6JF8), @BrownCSDept; previously @MIT_CSAIL, @Cambridge_CL. || @ms705 on BlueSky
24K Followers 4K FollowingAPI observability product @getpostman. Founded @akitasoftware (acquired 2023). Programming, APIs, and developer experience. Former professor @CSDatCMU.
7K Followers 180 Following@UCBerkeley security professor. Head of Security and Privacy Research @ Google DeepMind. MIT PhD. Co-founder of @OpaqueSys, @imua & @PreVeil.
410 Followers 290 FollowingCEO and Co-Founder @opaquesys. PhD in computer security @UCBerkeley. Ex @BCG and @IBMResearch.
I build privacy-preserving systems.