OctoML / Conversations

A recording of OctoML's first-ever builder's roundtable event! In this live, interactive discussion we unpacked the challenges, successes, and emerging opportunities for image generation in brand marketing, creative services, consumer apps, digital design, and AI art applications. Whether you’re building the next viral AI art app, designing interiors, building a library of custom imagery, or a brand new kind of application, there’s something for everyone.

Learn from our panel's firsthand experience navigating the complexities of working with image generation models like Stable Diffusion, SDXL, ControlNet, FILM and other models for creative applications.

Hear about the exciting advancements our panelists are looking forward to implementing in their projects, offering a glimpse into the future of AI generated imagery.

MLOps Coffee Sessions #121 with Luis Ceze, CEO and Co-founder of OctoML, Bringing DevOps Agility to ML co-hosted by Mihail Eric.

// Abstract
There'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.

// Bio
Luis 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 New York Times, Popular Science, MIT Technology Review, and the Wall Street Journal. Ceze is a Venture Partner at Madrona Venture Group and leads their technical advisory board.

// MLOps Jobs board
https://mlops.pallet.xyz/jobs

MLOps Swag/Merch
https://mlops-community.myshopify.com/

// Related Links
Landing page: https://octoml.ai/
The Boys in the Boat: Nine Americans and Their Epic Quest for Gold at the 1936 Berlin Olympics by Daniel James Brown: https://www.amazon.com/Boys-Boat-Americans-Berlin-Olympics/dp/0143125478

--------------- ✌️Connect With Us ✌️ -------------
Join our slack community: https://go.mlops.community/slack
Follow us on Twitter: @mlopscommunity
Sign up for the next meetup: https://go.mlops.community/register
Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/
Connect with Mihail on LinkedIn: https://www.linkedin.com/in/mihaileric/
Connect with Luis on LinkedIn: https://www.linkedin.com/in/luis-ceze-50b2314/

Timestamps:
[00:00] Introduction to Luis Ceze
[06:28] MLOps does not exist
[10:41] Semantics argument
[16:25] Parallel programming standpoint
[18:09] TVM
[22:51] Optimizations
[24:18] TVM in the ecosystem
[27:10] OctoML's further step
[30:42] Value chain
[33:58] Mature players
[35:48] Talking to SRE's and Machine Learning Engineers
[36:32] Building OctoML
[40:20] My Octopus Teacher
[42:15] Environmental effects of Sustainable Machine Learning
[44:50] Bridging the gap from OctoML to biological mechanisms
[50:02] Programmability
[57:13] Academia making the impact
[59:40] Rapid fire questions
[1:03:39] Wrap up

Machine learning (ML) has become a staple of data-driven technology and critical to the inner workings of modern companies. While 56% of enterprises have adopted ML models for critical use-cases, maximizing value from these models is challenging. Enterprises must manage the entire ML lifecycle – from data preparation to model monitoring – to generate valuable insights. On this panel, we will hear from several companies that are helping enterprises master this motion and uplevel their ML efforts.

Moderated By:
Julia Klein, Partner, March Capital (Confirmed)

Participants:
Luis Ceze, CEO, OctoML
Krishna Gade, CEO, Fiddler
Omri Geller, CEO, Run.ai

Luis Ceze, CEO, Co-Founder at OctoML, talks with John Furrier at Amazon re:MARS 2022 in Las Vegas, NV.

Luis 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.

From 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 libraries can improve system performance
20:10 Trade-offs between efficiency and complexity
24:35 Specialized instructions
26:34 The future of hardware design and research
30:03 Where does architecture and research go from here?
30:56 The environmental impact of efficiency
32:49 Optimizing and trade-offs
37:54 What is OctoML and the Octomizer?
42:31 Automating systems design with and for ML
44:18 ML and molecular biology
46:09 The challenges of deployment and post-deployment

🌟 Transcript: http://wandb.me/gd-luis-ceze 🌟

Links:
1. OctoML: https://octoml.ai/
2. "Scalable and Intelligent Learning Systems" (Chen, 2019): https://digital.lib.washington.edu/researchworks/handle/1773/44766
3. "Principled Optimization Of Dynamic Neural Networks" (Roesch, 2020): https://digital.lib.washington.edu/researchworks/handle/1773/46765
4. "Cross-Stack Co-Design for Efficient and Adaptable Hardware Acceleration" (Moreau, 2018): https://digital.lib.washington.edu/researchworks/handle/1773/43349
5. "TVM: An Automated End-to-End Optimizing Compiler for Deep Learning" (Chen et al., 2018): https://www.usenix.org/system/files/osdi18-chen.pdf
6. Porcupine is a molecular tagging system introduced in "Rapid and robust assembly and decoding of molecular tags with DNA-based nanopore signatures" (Doroschak et al., 2020): https://www.nature.com/articles/s41467-020-19151-8

---

🎙 Get our podcasts on these platforms:
Soundcloud: http://wandb.me/soundcloud
Apple Podcasts: http://wandb.me/apple-podcasts
Spotify: http://wandb.me/spotify
Google: http://wandb.me/gd_google
YouTube: http://wandb.me/youtube


Join our community of ML practitioners where we host AMAs, share interesting projects and meet other people working in Deep Learning:
http://wandb.me/fs

Check out Fully Connected, which features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, industry leaders sharing best practices, and more:
https://wandb.ai/fully-connected

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
Podcast site: https://discopossepodcast.com​​​​
iTunes: https://podcasts.apple.com/ca/podcast...​
Spotify: https://open.spotify.com/show/6S6s7oY...​

SPONSORED BY:

Veeam Software - https://vee.am/DiscoPosse​​​​
Velociy Closing - https://velocityclosing.com​​​
Diabolical Coffee - https://diabolicalcoffee.com

Check the episode page here: https://discopossepodcast.com/ep-154-machine-learning-optimization-for-all-with-luis-ceze-of-octoml/

#MachineLearning #Startup #Founder #OctoML

Coffee with Jason Knight, Co-founder, and CPO at OctoML.
Joined by our guest host, Karl Fezer, Arm AI Evangelist, we got to know Jason and his amazing career. We then dove into the world of machine learning compilers and TVM. We talked about the contributions Arm is making to TVM and the work done by OctoML.

We look forward to having you with us every week. Same time, same place. So prepare your coffee or favorite tea, and join in on the fun Arm tech conversations.

Innovation Coffee - live, every Thursday - 10 am PT (6 pm UTC)

#InnovationCoffee #MachinLearning #OctoML

○○○ Episode resources ○○○
TVM 2020 Blog: https://community.arm.com/developer/ip-products/processors/b/ml-ip-blog/posts/tvm-2020
TinyML - How TVM is Taming Tiny: https://tvm.apache.org/2020/06/04/tinyml-how-tvm-is-taming-tiny
OctoML: https://octoml.ai/
TVM: https://tvm.apache.org/community

○○○ Get to know the Guest ○○○
Jason's Twitter: https://twitter.com/binarybana

○○○ Arm Software Developer Resources ○○○
Twitter: https://twitter.com/ArmSoftwareDev
GitHub: https://github.com/arm-software
Discord: https://discord.gg/deveco
Arm Developer: https://developer.arm.com/

○○○ Get to know the hosts ○○○
https://twitter.com/AlessandroDevs
https://twitter.com/fixxxxxxer
https://twitter.com/KarlFezer