OctoML

👋 Hi machine learning developers, researchers and practitioners. Want to learn how to make your ML run faster and easier to deploy to GPUs, CPUs and accelerators?

TVMCon registration is now open and today we're announcing our first round of speakers!

TVMCon registration is open and speakers announced RSVP for free to join the Apache TVM community December 15-17 for TVMCon! The 2021 Apache TVM and Open Source ML Acceleration Conference will be an all-virtual event...

🎉 We just raised $85M in Series C to accelerate machine deployment for enterprises everywhere!

OctoML Raises $85M Series C to Accelerate ML Deployment for Enterprises OctoML has raised $85M led by Tiger Global Management, with participation from existing investors Addition, Madrona Venture Group and Amplify Partners.

We're joining forces with Qualcomm, AMD & Arm:

"These three partnerships may signal just the beginning for OctoML, whose founders hope to “empower enterprises to create a unified deployment lifecycle across all their ML hardware vendors” said Ceze."

OctoML Makes Machine Learning Accessible to Almost Anyone Discover the latest artificial intelligence news, jobs and more.

At NVIDIA on Nov 11 @ 7am PST, check out session A31090 to hear about the next generation of improvements in
Apache TVM such as ML-powered TensorCore Code Generation by Jason Knight and Junru Shao!

Watch GTC 2021 Conference Sessions On-Demand Free registration. November 8-11, 2021

The first hardware target from our collaboration with is now available in OctoML! Check out why the Cortex-A72 processor could be a perfect fit for your edge machine learning deployments.

https://octoml.ai/blog/accelerating-machine-learning-at-the-edge-arm-cortex-a72

Now you can use Apache TVM with Swift to develop ML apps for the Apple ecosystem. Check out the sample image classification app in our tutorial blog:

Using Swift and Apache TVM to develop ML apps for the Apple ecosystem We are excited to announce that now you can bring many more machine learning models to the Apple ecosystem via Apache TVM.

Earlier this week at , Phil Mazenett presented a short demo of how OctoML and VMware work better together with OctoML delivering ML model acceleration and VMWare providing great infrastructure to run AI at high performance.

Check it out:

OctoML and VMware - Better Together Demo Earlier this week at VMworld, we presented a short demo of how OctoML and VMware work better together with OctoML delivering ML model acceleration and VMWare...

We're excited to share our collaboration with AMD to bring the machine learning model optimization power of Apache TVM to AMD's full suite of hardware (CPUs, APUs and GPUs) from the cloud to the edge.

OctoML and AMD partner to speed-up ML deployments from cloud to edge We're excited to share our collaboration with AMD around Apache TVM and the OctoML Machine Learning Deployment Platform. Now our customers can deploy ML apps easily on AMD hardware

Do you make machine learning run faster? We'd love to hear about your ML acceleration research, work and projects at the 4th Apache TVM and Open Source ML Acceleration Conference this December. Please submit your talk by Oct 15th:

Share your machine learning acceleration insights at TVMcon 2021 The Call For Proposals for the fourth annual TVMcon (Dec 15-17) is open till October 15. We encourage you to submit your machine learning acceleration talk!

The MLPerf results released this week contain the first two pioneering inference benchmarks accelerated via Apache TVM and automated with the MLCommons Collective Knowledge framework.

We’re creating a blueprint for future submissions that will be completely vendor, hardware and ML framework agnostic - while still delivering world-class results. Join us:

OctoML joins the community effort to democratize MLPerf inference benchmarking OctoML enters the MLPerf inference benchmark with the first two submissions accelerated via Apache TVM and automated with MLCommons' Collective Knowledge framework.

Want more hardware options for deploying your machine learning models to production?

OctoML now supports inferencing targets from multiple clouds to the edge, including hardware from leading industry vendors like AWS, GCP, NVIDIA, AMD, Arm, and Intel.

OctoML expands deployment choice with new multi-cloud and edge targets The OctoML Deployment Platform now supports inferencing targets from the cloud to the edge, including hardware from industry vendors like AWS, GCP, NVIDIA, AMD, Arm, and Intel.