Shows
The Confident CommitAchieving AI development at scale ft. Luis Ceze of OctoAIIn this episode, Rob is joined by Luis Ceze, CEO of OctoAI and a distinguished professor of computer science at the University of Washington. Together, they unpack the surge of interest in AI, attributing it to the convergence of factors like the unprecedented availability of data thanks to the internet boom and the accessibility of powerful computing resources.Their conversation delves into the pragmatic challenges developers face, such as striking the right balance between cost-effectiveness, inference speed, and ensuring scalability and availability. Luis explains how OctoAI is pioneering solutions to streamline this process, empowering developers to navigate...
2024-02-2329 min
The CloudcastEconomics & Optimization of AI/MLLuis Ceze (@luisceze, Founder/CEO @OctoML) talks about barriers to entry for AI & ML, the economics of funding, training, fine tuning, inferencing and optimizations.SHOW: 749CLOUD NEWS OF THE WEEK - http://bit.ly/cloudcast-cnotwNEW TO CLOUD? CHECK OUT - "CLOUDCAST BASICS"SHOW SPONSORS:CloudZero – Cloud Cost Visibility and SavingsCloudZero provides immediate and ongoing savings with 100% visibility into your total cloud spendReduce the complexities of protecting your workloads and applications in a multi-cloud environment. Panoptica provides comprehensive cloud workload protection integr...
2023-08-3035 min
Infinite Curiosity Pod with Prateek JoshiSpeeding up Generative AI models | Luis Ceze, cofounder and CEO of OctoMLLuis Ceze is the cofounder and CEO of OctoML, a platform that offers compute infrastructure to fine-tune, run, and scale your AI models. He's a professor at University of Washington and a venture partner at Madrona. He was previously the cofounder of Corensic. He has a PhD in Computer Science from University of Illinois Urbana-Champaign. In this episode, we cover a range of topics including: - OctoAI product announcement - How to make LLMs faster and cheaper - Training your own LLMs - The perceived shortage of AI compute ...
2023-07-3139 min
Science in ParallelBeyond Exascale: Exploring Emerging Processors The exascale era in computing has arrived, and that brings up the question of what's next. We'll discuss some emerging processor technologies-- molecular storage and computing, quantum computing and neuromorphic chips—with an expert from each of those fields. Learn more about these technologies' strengths and challenges and how they might be incorporated into tomorrow's systems. You'll meet: Luis Ceze, professor of computer science at the University of Washington and CEO of the AI startup OctoML. Bert de Jong, senior scientist and department head for computational sciences at Lawrence Berkeley National Laboratory and dep...
2023-06-2141 min
MLOps.communityCost/Performance Optimization with LLMs [Panel]Sign up for the next LLM in production conference here: https://go.mlops.community/LLMinprod
Watch all the talks from the first conference: https://go.mlops.community/llmconfpart1
// Abstract
In this panel discussion, the topic of the cost of running large language models (LLMs) is explored, along with potential solutions. The benefits of bringing LLMs in-house, such as latency optimization and greater control, are also discussed. The panelists explore methods such as structured pruning and knowledge distillation for optimizing LLMs. OctoML's platform is mentioned as a tool for the automatic deployment of custom models and...
2023-05-0635 min
MLOps.communityBringing DevOps Agility to ML// Luis Ceze // Coffee Sessions #121MLOps Coffee Sessions #121 with Luis Ceze, CEO and Co-founder of OctoML, Bringing DevOps Agility to ML, co-hosted by Mihail Eric. Join the Community: https://go.mlops.community/YTJoinInGet the newsletter: https://go.mlops.community/YTNewsletter// AbstractThere's something about this idea where people see a future where you don't need to think about infrastructure. You should just be able to do what you do, and infrastructure happens. People understand that there is a lot of complexity underneath the hood, and most data scientists or machine learning engineers start deploying things, and shouldn't have to worry about the most efficient way of doing this.// BioLuis Ceze is Co-Founder and CEO of OctoML, which enables businesses to seamlessly deploy ML models to production, making the most out of the hardware. OctoML is backed by Tiger Global, Addition, Amplify Partners, and Madrona Venture Group. Ceze is the Lazowska Professor in the Paul G. Allen School of Computer Science and Engineering at the University of Washington, where he has taught for 15 years.Luis co-directs the Systems and Architectures for Machine Learning lab (sampl.ai), which co-authored Apache TVM, a leading open-source ML stack for performance and portability that is used in widely deployed AI applications. Luis is also co-director of the Molecular Information Systems Lab (misl.bio), which led pioneering research in the intersection of computing and biology for IT applications such as DNA data storage. His research has been featured prominently in the media, including the New York Times, Popular Science, MIT Te
2022-09-061h 04
Founded & FundedIA40 Spotlight: Hugging Face CEO Clem Delangue and OctoML CEO Luis Ceze on foundation models, open source, and transparencyThis week on Founded and Funded, we spotlight our next IA40 winners – Hugging Face and OctoML. Managing Director Matt McIlwain talks to Hugging Face Co-founder and CEO Clem Delangue and OctoML Co-founder and CEO Luis Ceze all about foundation models, diving deep into the importance of detecting biases in the data being used to train models as well the importance of transparency and the ability for researchers to share their models. They discuss open source, business models, the role of cloud providers and debate DevOps versus MLOps, something that Luis feels particularly passionate about. Clem even explains how large models ar...
2022-05-0545 min
Practical AIMLOps is NOT RealWe all hear a lot about MLOps these days, but where does MLOps end and DevOps begin? Our friend Luis from OctoML joins us in this episode to discuss treating AI/ML models as regular software components (once they are trained and ready for deployment). We get into topics including optimization on various kinds of hardware and deployment of models at the edge.Join the discussionChangelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!Sponsors:Changelog++ – You love our content and you want to take it...
2022-04-2645 min
Changelog Master FeedMLOps is NOT Real (Practical AI #176)We all hear a lot about MLOps these days, but where does MLOps end and DevOps begin? Our friend Luis from OctoML joins us in this episode to discuss treating AI/ML models as regular software components (once they are trained and ready for deployment). We get into topics including optimization on various kinds of hardware and deployment of models at the edge.
2022-04-2645 min
The New Stack PodcastDeploying Scalable Machine Learning Models for Long-Term SustainabilityAs machine learning models proliferate and become sophisticated, deploying them to the cloud becomes increasingly expensive. This challenge of optimizing the model also impacts the scale and requires the flexibility to move the models to different hardware like Graphic Processing Units (GPUs) or Central Processing Units (CPUs) to gain more advantage. The ability to accelerate the deployment of machine learning models to the cloud or edge at scale is shifting the way organizations build next-generation AI models and applications. And being able to optimize these models quickly to save costs and sustain them over time is moving to the...
2022-01-1115 min
Intel on AIComputing with DNAIn this episode of Intel on AI host Amir Khosrowshahi and Luis Ceze talk about building better computer architectures, molecular biology, and synthetic DNA. Luis Ceze is the Lazowska Professor in the Paul G. Allen School of Computer Science and Engineering at the University of Washington, Co-founder and CEO at OctoML, and Venture Partner at Madrona Venture Group. His research focuses on the intersection between computer architecture, programming languages, machine learning and biology. His current research focus is on approximate computing for efficient machine learning and DNA-based data storage. He co-directs the Molecular Information Systems Lab (misl...
2021-12-2238 min
Software Engineering Radio - the podcast for professional software developersEpisode 479: Luis Ceze on the Apache TVM Machine Learning CompilerLuis Ceze of OctoML discusses Apache TVM, an open source machine learning model compiler for a variety of different hardware architectures with host Akshay Manchale. Luis talks about the challenges in deploying models on specialized hardware and how TVM.
2021-09-2951 minSoftware Engineering Radio - The Podcast for Professional Software DevelopersEpisode 479: Luis Ceze on the Apache TVM Machine Learning CompilerLuis Ceze of OctoML discusses Apache TVM, an open source machine learning model compiler for a variety of different hardware architectures with host Akshay Manchale. Luis talks about the challenges in deploying models on specialized hardware and how TVM.
2021-09-2951 minSoftware Engineering Radio - the podcast for professional software developersEpisode 479: Luis Ceze on the Apache TVM Machine Learning CompilerLuis Ceze of OctoML discusses Apache TVM, an open source machine learning model compiler for a variety of different hardware architectures with host Akshay Manchale. Luis talks about the challenges in deploying models on specialized hardware and how TVM.
2021-09-2951 min
2021-08-0531 min
Gradient Dissent: Conversations on AILuis Ceze — Accelerating Machine Learning SystemsFrom Apache TVM to OctoML, Luis gives direct insight into the world of ML hardware optimization, and where systems optimization is heading.
---
Luis Ceze is co-founder and CEO of OctoML, co-author of the Apache TVM Project, and Professor of Computer Science and Engineering at the University of Washington. His research focuses on the intersection of computer architecture, programming languages, machine learning, and molecular biology.
Connect with Luis:
📍 Twitter: https://twitter.com/luisceze
📍 University of Washington profile: https://homes.cs.washington.edu/~luisceze/
---
⏳ Timestamps:
0:00 Intro and sneak peek
0:59 What is TVM?
8:57 Freedom of choice in software and hardware stacks
15:53 How new...
2021-06-2448 minPractical AIApache TVM and OctoML90% of AI / ML applications never make it to market, because fine tuning models for maximum performance across disparate ML software solutions and hardware backends requires a ton of manual labor and is cost-prohibitive. Luis Ceze and his team created Apache TVM at the University of Washington, then left founded OctoML to bring the project to market.Join the discussionChangelog++ members get a bonus 1 minute at the end of this episode and zero ads. Join today!Sponsors:O'Reilly Media – Learn by doing — Python, data, AI, machine learning, Kubernetes, Docker, and more. Just open...
2021-05-1849 min
What the Dev?Making AI more accessible to developers with OctoML CEO Luis Ceze - Episode 102In this week's episode we spoke with Luis Ceze, professor at the University of Washington, co-creator of the Apache TVM project, and co-founder and CEO of OctoML. He spoke about how open source projects like Apache TVM make AI and machine learning more accessible to developers, as well as the foundations that need to be in place to increase AI adoption.
2021-05-1117 min
Utilizing Tech - The Podcast Series about New and Emerging Technologies2x14: Using ML to Optimize ML with Luis Ceze of OctoMLTraining and optimizing a machine learning model takes a lot of compute resources, but what if we used ML to optimize ML? Luis Ceze created Apache Tensor Virtual Machine (TVM) to optimize ML models and has now founded a company, OctoML, to leverage this technology. Fundamentally, machine learning relies on linear algebra, but how should we pick the fastest approach for each model? Today this is done with human intuition, but TVM builds machine learning models to predict the best approaches to try. It also creates an executable so the model can run best on various target hardware platforms...
2021-04-0630 min
DiscoPosse PodcastEp 154 Machine Learning Optimization for All with Luis Ceze of OctoML
Luis Ceze is a computer architect and co-founder and CEO of OctoML. I do research in the intersection of computer systems architecture, programming languages, machine learning and biology.
OctoML is doing some very cool things about demecratizing ML and transforming how ML models are optimized and made secure for deployment. Luis shares a lot of great info on the foundations of ML, ethics of data, and how he builds a team.
Check out OctoML online at https://octoml.ai
This episode is sponsored by ...
2021-02-171h 11
Machine Learning Archives - Software Engineering DailyOctoML: Automated Deep Learning Engineering with Jason Knight and Luis Ceze
The incredible advances in machine learning research in recent years often take time to propagate out into usage in the field. One reason for this is that such “state-of-the-art” results for machine learning performance rely on the use of handwritten, idiosyncratic optimizations for specific hardware models or operating contexts. When developers are building ML-powered systems to deploy in the cloud and at the edge, their goals to ensure the model delivers the best possible functionality and end-user experience- and importantly, their hardware and software stack may require different optimizations to achieve that goal.
OctoML provides a Sa...
2021-02-0953 min
Software Engineering DailyOctoML: Automated Deep Learning Engineering with Jason Knight and Luis CezeThe incredible advances in machine learning research in recent years often take time to propagate out into usage in the field. One reason for this is that such “state-of-the-art” results for machine learning performance rely on the use of handwritten, idiosyncratic optimizations for specific hardware models or operating contexts. When developers are building ML-powered systems to deploy in the cloud and at the edge, their goals to ensure the model delivers the best possible functionality and end-user experience- and importantly, their hardware and software stack may require different optimizations to achieve that goal.OctoML provides a SaaS prod...
2021-02-0950 min
the bioinformatics chatDNA tagging and Porcupine with Kathryn DoroschakPorcupine is a molecular tagging system—a way to tag physical
objects with pieces of DNA called molecular bits, or molbits for short.
These DNA tags then can be rapidly sequenced on an Oxford Nanopore MinION
device without any need for library preparation.
In this episode, Katie Doroschak explains how Porcupine works—how molbits
are designed and prepared, and how they are directly recognized by the
software without an intermediate basecalling step.
Links:
Porcupine: Rapid and robust tagging of physical objects using nanopore-orthogonal DNA strands (Kathryn Doroschak, Karen Zhang, Melissa Queen, Aishwarya Mandyam, Karin Stra...
2020-04-2945 min