Trending...
- Phinge Exposes Massive AI Security Risks, Claiming Its Patented Hardware-Verified Architecture Is The Only Safeguard Against Surveillance Capitalism
- On the Boards: Proform Builds Announce New Construction in Alki, Seattle
- Phinge's Netverse: Reclaiming the Digital Frontier For Everyone Through CEO Robert DeMaio's Vision of a True App-less, User Data Sovereign World
SEATTLE, Sept. 16, 2021 /PRNewswire/ -- OctoML today announced a collaboration with Qualcomm Technologies, Inc. to provide first-class Apache TVM support for Snapdragon® platforms and SoCs.
As part of this collaboration, OctoML has a strategic agreement to work closely with the Qualcomm's® Tensor Virtual Machine (TVM) compiler team to extend Apache TVM for Qualcomm® Hexagon™ processors. As a result, it is expected that Apache TVM will be enhanced to address the unique characteristics of Hexagon in order to make it a demonstrated leader in AI performance on power-constrained devices. These enhancements will be designed to drive fundamental innovation in Apache TVM that should benefit the entire Apache TVM community.
Built on the Apache TVM open-source framework, OctoML's Platform provides an automation framework that optimizes trained models to achieve optimal performance across a breadth of hardware endpoints and cloud services—without compromising accuracy. The platform readily addresses the challenge of optimizing ML models to match the resources at the edge, which opens up opportunities for a new wave of intelligent apps.
More on Washingtoner
"We are excited to be working with OctoML to further expand Apache TVM coverage to our Qualcomm® AI Engine to help accelerate the deployment of ML applications and optimize models in the future," Jeff Gehlhaar, VP of Technology, Qualcomm Technologies, Inc.
This collaboration is made possible through Qualcomm Technologies' support of Apache TVM. Apache TVM is a software framework that provides a unified layer between the leading machine learning frameworks—like Tensorflow and Pytorch—and the vast array of hardware solutions. This innovation means that ML models can be deployed anywhere from cloud to edge to mobile.
"OctoML's ability to fully utilize hardware capabilities for machine learning, combined with the automation and accessibility of our SaaS platform, will greatly simplify the deployment of ML innovation across Qualcomm Technologies' powerful hardware," said Luis Ceze, CEO and co-founder, OctoML. "We are very excited to work with Qualcomm Technologies to unlock the power of their SoCs on our platform and enable the next-generation of ML applications at the edge."
More on Washingtoner
Visit here to register for OctoML's limited access program.
Qualcomm, Snapdragon, and Hexagon are trademarks or registered trademarks of Qualcomm Incorporated.
Snapdragon, Qualcomm Hexagon, and Qualcomm AI Engine are products of Qualcomm Technologies, Inc. and/or its subsidiaries.
About OctoML
OctoML is a machine learning acceleration platform based in Seattle, Washington. OctoML aims to accelerate model performance while enabling seamless deployment of models across any hardware platform, cloud provider, or edge device. The company's investors include Addition, Madrona Venture Group, and Amplify Partners. OctoML was founded by creators of open-source Apache TVM, CEO Luis Ceze, CTO Tianqi Chen, CPO Jason Knight, Chief Architect Jared Roesch, and VP of Technology Partnerships Thierry Moreau. For more information, please visit https://octoml.ai/
SOURCE OctoML
As part of this collaboration, OctoML has a strategic agreement to work closely with the Qualcomm's® Tensor Virtual Machine (TVM) compiler team to extend Apache TVM for Qualcomm® Hexagon™ processors. As a result, it is expected that Apache TVM will be enhanced to address the unique characteristics of Hexagon in order to make it a demonstrated leader in AI performance on power-constrained devices. These enhancements will be designed to drive fundamental innovation in Apache TVM that should benefit the entire Apache TVM community.
Built on the Apache TVM open-source framework, OctoML's Platform provides an automation framework that optimizes trained models to achieve optimal performance across a breadth of hardware endpoints and cloud services—without compromising accuracy. The platform readily addresses the challenge of optimizing ML models to match the resources at the edge, which opens up opportunities for a new wave of intelligent apps.
More on Washingtoner
- Gravity Payments and Suno Software Partner to Simplify Payments for Independent Hearing Clinics
- Where Do Missouri Plane Crashes Really Happen? Not Where You'd Think
- Spokane: Female Arrested After Homeowners Caught Her on Property of Burned Home
- SPD Detectives are Investigating a Suspicious Death in West Spokane
- LCC Asia Pacific Sponsors CubeSatPlus 2026 at UNSW Sydney
"We are excited to be working with OctoML to further expand Apache TVM coverage to our Qualcomm® AI Engine to help accelerate the deployment of ML applications and optimize models in the future," Jeff Gehlhaar, VP of Technology, Qualcomm Technologies, Inc.
This collaboration is made possible through Qualcomm Technologies' support of Apache TVM. Apache TVM is a software framework that provides a unified layer between the leading machine learning frameworks—like Tensorflow and Pytorch—and the vast array of hardware solutions. This innovation means that ML models can be deployed anywhere from cloud to edge to mobile.
"OctoML's ability to fully utilize hardware capabilities for machine learning, combined with the automation and accessibility of our SaaS platform, will greatly simplify the deployment of ML innovation across Qualcomm Technologies' powerful hardware," said Luis Ceze, CEO and co-founder, OctoML. "We are very excited to work with Qualcomm Technologies to unlock the power of their SoCs on our platform and enable the next-generation of ML applications at the edge."
More on Washingtoner
- Spokane: City Council Approves Mayor's Orders for Declaration of Emergency
- Real Estate Syndication Attorney Tilden Moschetti Releases The Real Estate Private Equity Blueprint
- 5X Gross Margin Improvement to Beat EPS Consensus; $54.6 Million 10-Year Contract Award Puts Cybersecurity Leader on Path to a $30 Million Run Rate
- Independent Colbert Packaging Thrives Amid Industrywide Consolidation
- Free Commercial Glass Estimating and Code Compliance Tools Launched by Landmark Construction - The Leading Glass Company in Los Angeles
Visit here to register for OctoML's limited access program.
Qualcomm, Snapdragon, and Hexagon are trademarks or registered trademarks of Qualcomm Incorporated.
Snapdragon, Qualcomm Hexagon, and Qualcomm AI Engine are products of Qualcomm Technologies, Inc. and/or its subsidiaries.
About OctoML
OctoML is a machine learning acceleration platform based in Seattle, Washington. OctoML aims to accelerate model performance while enabling seamless deployment of models across any hardware platform, cloud provider, or edge device. The company's investors include Addition, Madrona Venture Group, and Amplify Partners. OctoML was founded by creators of open-source Apache TVM, CEO Luis Ceze, CTO Tianqi Chen, CPO Jason Knight, Chief Architect Jared Roesch, and VP of Technology Partnerships Thierry Moreau. For more information, please visit https://octoml.ai/
SOURCE OctoML
0 Comments
Latest on Washingtoner
- Space Ambitions Expanding as New Testing Builds on NASA Results and Targets MEO, GEO and Next-Generation Orbital Markets: Ascent Solar Technologies
- FDA Path Clears, Manufacturing Ramps Up + $22.3 Million Strengthens the Balance Sheet; Inflection Point for NRx Pharmaceuticals (N A S D A Q: NRXP)
- Buy Retatrutide Research Peptide: Why Reta Is Getting So Much Attention
- Stage 2 Burn Ban Order in Effect Across Tacoma
- San Diego Attorney Anthony Z. Vargas Narrows Practice to Employment Law, Representing Employees Only
- Spokane: Additional PPE Kits Available Tuesday and Thursday
- Solid Earth Introduces RealtyID, a Universal Identity Spine for the Real Estate Industry
- BlazeHive's AI SEO Agent Outranks Human Writers on 500+ Google Top-3 Results in 5 Months, on Autopilot
- Cracking the Immortality Code: A Human / AI Long-Term Collaboration Working to Achieve Immortality
- On the Boards: Proform Builds Announce New Construction in Alki, Seattle
- On the Boards: Proform Builds Announce New Construction in Gig Harbor
- Phinge Exposes Massive AI Security Risks, Claiming Its Patented Hardware-Verified Architecture Is The Only Safeguard Against Surveillance Capitalism
- Phinge & CEO Robert DeMaio Publicly Declare Cash Settlements or Judgments Alone Cannot & Will Not Remedy the Deep Public Harm of Infringing Its IP
- Dana Flanagan Expands the Authority Architect, Bringing a Nontraditional Approach to Executive Authority, Strategic Access and Business Growth
- Phinge's Netverse: Reclaiming the Digital Frontier For Everyone Through CEO Robert DeMaio's Vision of a True App-less, User Data Sovereign World
- DuraFast Label Company Launches Seiko SLP850 2" Thermal Printer with Free Label Promotion
- Scientific Figure Releases Free Layout Template Libraries for Graphical Abstracts and Research Posters
- Permian Museum announces the addition of an Ancient Alien Artifacts photo gallery
- VISION 2050 Award for Historic Tideflats Subarea Plan Presented by Puget Sound Regional Council at Tacoma City Council Meeting
- The Golden Jazz Fest Shuttle Returns for 2026