Event Review | Gathering Industry Technology Experts and Sharing Moments of Thought Collision, 2023 Meet TVM · Beijing Station Concluded Successfully
Contents at a glance:"2023 Meet TVM Beijing Station" was successfully held at Zhongguancun Garage Coffee on June 17, attracting more than 150 participants from companies and universities, and everyone had a full and heated discussion.
Keywords:Machine Learning Compilation 2023 Meet TVM
This article was first published on HyperAI WeChat public platform~
On June 17, the second offline gathering of 2023 Meet TVM, hosted by MLC.AI and HyperAI and co-organized by OpenBayes, came to a successful conclusion.
We are honored to have invited 7 technical experts from Shanghai Jiao Tong University, ARM China, Horizon Robotics and NIO.Combining the application cases of AI compiler in its own business scenarios, it brought wonderful sharing to the friends on site.
In addition to local friends in Beijing, many friends from Tianjin, Nanjing, Hangzhou, Shanghai and other places also joined. Everyone brought their own business questions and challenges, and in addition to listening to technical sharing, they also had active exchanges and discussions with their peers.
Get the presentation PPT and live video
The following is a brief introduction to the event and a video review of the event.
Follow the WeChat public account "HyperAI 超神经元", reply with the keyword TVM 北京 in the background, and get the complete PPT of the guest.
Share topic:Deploy language models to any device using MLC-LLM
Contents:Significant progress has been made in the field of generative AI and large language models (LLMs), which have remarkable capabilities and the potential to fundamentally change many fields. Currently, most of these models require strong computing power and memory requirements and cannot be deployed on personal PCs, mobile phones, and smaller end-side devices. MLC-LLM optimizes the running speed and memory requirements through compilation technology, making it possible to deploy LLMs on the end-side, providing a new infrastructure for the subsequent development of language models.
Live video:
https://www.bilibili.com/video/BV1rm4y1Y7Si/?spm_id_from=333.999.0.0
Share topic:TVM at ARM China
Contents:With the booming development of AI applications, various NPU chips are used on edge devices to accelerate AI applications. How to quickly adapt to various machine learning frameworks and operating systems has become a problem. Through the integration of its own tool chain and TVM, ARM China has realized multiple practical functions such as graph splitting and automatic heterogeneous execution, helping customers quickly deploy AI applications on ARM China Zhouyi NPU chips.
Live video:
https://www.bilibili.com/video/BV1GW4y1X7tL/?spm_id_from=333.337.search-card.all.click
Share topic:AI heterogeneous programming and compilation practice
Contents:AI chips are evolving towards tightly coupled heterogeneity, and the programmability and performance optimization of chips are key issues that the industry has been trying to solve. This sharing mainly introduces some of Horizon's practices in AI compilation optimization, programmability, etc., and conducts in-depth discussions on some key issues.
Live video:
https://www.bilibili.com/video/BV1js4y117NT/?spm_id_from=333.337.search-card.all.click
Share topic:TVM at NIO
Contents:The field of autonomous driving is a field with both challenges and opportunities. With the iteration of products and users' increasingly higher requirements for driving experience, common AI engines cannot efficiently and safely support complex product production lines. We developed NIO's self-developed AI compiler based on TVM, which solved some common problems in the field of autonomous driving and formed a systematic solution and technical architecture.
Three engineers from NIO, Meng Tong, Chen Xi (Zhihu aaronxic), and Wang Lulu, gave detailed explanations of the technologies and architectures involved.
Live video:
https://www.bilibili.com/video/BV1fV4y117g7/?spm_id_from=333.337.search-card.all.click
Share topic:Dynamic neural network compilation optimization
Contents: Dynamic neural networks show important advantages over static neural networks in terms of accuracy, computational efficiency, and adaptability. However, existing deep learning frameworks and compilers mainly focus on optimizing static networks with deterministic execution, missing out on optimization opportunities in dynamic networks. The key to optimizing dynamic networks is to track the flow of data in them. This sharing details our work on dynamic neural network compilation.
Live video:
https://www.bilibili.com/video/BV1Mz4y1v7se/?spm_id_from=333.337.search-card.all.click
Join TVM Chinese Community to unlock more cities
Following the Shanghai meeting in March and the Beijing meeting in June, we are very happy to gather engineers who are interested in AI compilers in different cities to provide a platform for peer communication and exchange of knowledge. The third offline meetup of this year is planned to be held in Shenzhen in September. At that time, we welcome all enterprises and community partners to participate in the co-creation and continuously expand the influence of the TVM Chinese community!
also,We are also actively recruiting TVM Chinese community contributors.If you want to become a member of us, please feel free to add WeChat antonia0912. We look forward to your enthusiastic joining!
We are currently recruiting:
* TVM Chinese documentation translation volunteers ensure that Chinese documentation is kept in sync with English documentation, and provide infrastructure for more engineers who want to learn and understand TVM (visit the official website: tvm.hyper.ai)!
* Activity volunteers, responsible for organizing, planning and executing activities in various places, and establishing our base in multiple Internet centers across the country.
* Q&A volunteers, familiar with TVM and willing to contribute insights and ideas to friends in the community who encounter problems, to help everyone solve technical problems.
More cities will be unlocked in 2023. Join us to create the most active AI compiler community in China!
Finally, let’s take a group photo on the scene❤️
Introduction to the organizers and partners
As the organizer of this event, MLC.AI Community (https://mlc.ai/) was founded in June 2022, and led by Chen Tianqi, the main inventor of Apache TVM and a well-known young scholar in the field of machine learning, the team launched the MLC online course, which systematically introduced the key elements and core concepts of machine learning compilation.
In November 2022, with the joint efforts of MLC.AI community volunteers,The first complete TVM Chinese document was launched and successfully hosted on the HyperAI official website.It further provides domestic developers who are interested in machine learning compilation with the infrastructure - documentation - to access and learn a new technology.
In 2023, the community will launch the "2023 Meet TVM" series of activities in many cities across the country, and welcomes enterprises and community partners to participate in co-creation.
MLC Online Courses:https://mlc.ai/
TVM Chinese Documentation:https://tvm.hyper.ai/
HyperAI is China's leading artificial intelligence and high-performance computing community.We are committed to providing high-quality public resources in the field of data science to domestic developers.So far, it has provided domestic download nodes for more than 1,200 public data sets, supported more than 300 artificial intelligence and high-performance computing related term queries, hosted the complete TVM Chinese documentation, and will soon launch multiple basic and popular tutorials.
Visit the official website:https://orion.hyper.ai/
OpenBayes is a leading high-performance computing service provider in China. By grafting classic software ecosystems and machine learning models onto new-generation heterogeneous chips, it provides faster and easier-to-use data science computing products for industrial enterprises and university scientific research. Its products have been adopted by dozens of large industrial scenarios or leading scientific research institutes.
Visit the official website:https://openbayes.com/
Garage Coffee is a platform that brings together entrepreneurs. Relying on the coffee shop, it provides start-ups with a one-stop comprehensive investment and financing solution, helping project parties to quickly raise funds and promote rapid development. At the same time, it provides high-quality value-added services such as entrepreneurship counseling, resource matching, publicity and reporting, and helps investors quickly discover good projects, providing a basis for their lead investment, follow-up investment, resource output, experience output, etc., and promoting collaborative development among multi-level investor groups.
This article was first published on HyperAI WeChat public platform~