Event Preview | 2023 Meet TVM · Beijing Station Is Scheduled, Which of the 5 Talks Are You Most Looking Forward To?
Contents at a glance:The second stop of the 2023 Meet TVM offline party is scheduled for June 17! This time we have set up 5 talks and look forward to meeting everyone in Zhongguancun, Beijing!
Keywords:Compiler Offline Event 2023MeetTVM
This article was first published on HyperAI WeChat public platform~
On March 4, the first offline event of 2023 Meet TVM was successfully held in Shanghai. More than 100 engineers engaged in AI compiler development and paying attention to the development of TVM gathered in Wujiaochang for full and heated discussions and exchanges.
Read previous articles:Event Review | 2023 Meet TVM first gathered in Shanghai, more than 100 engineers discussed the present and future of machine learning compilation
After more than 3 months, the much-anticipated and long-awaited offline gathering in Beijing is finally here!We invited 5 senior AI compiler experts to share their experience with the audience through application cases and best practices in real scenarios.
2023 Meet TVM Beijing Event Information
⏰ time:June 17 (Saturday) 14:00-18:00
📍 Place:Garage Cafe, No. 48 Haidian West Street, Haidian District
👬 Number of people:100 (limited seats, please register as early as possible)
🙌🏻 Sign up:Scan the QR code below to register (choose one of the two options: activity line or hundred grid)
Active row:Scan the QR code to jump to the event registration
Baige Activities:Scan the QR code to jump to the Baige event registration
Scan the QR code and note "TVM Beijing" to join the event group
📝 Schedule:
Click on the image to view the full agenda
Brief introduction of guests and content
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.
Watch this sharing session and you will learn:
1. Challenges in deploying large models
2. The role of machine learning compilation (MLC) technology in large model scenarios
3. Technical details behind MLC-LLM
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.
Watch this sharing session and you will learn:
1. Introduction to ARM China Zhouyi NPU
2. Implementation of graph splitting and automatic heterogeneous execution based on BYOC framework
3. TVM RPC system construction and use
4. Commercial-quality TVM release solution
5. How to quickly locate model accuracy issues
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 will mainly introduce some of Horizon's practices in AI compilation optimization, programmability, etc., and discuss some key issues with you in depth.
Watch this sharing session and you will learn:
1. Evolution trend of AI chip architecture
2. Some practical experience of AI compilation optimization
3. Some explorations on AI chip programmability
Share topic:TVM at NIO
Contents:The field of autonomous driving is a field where challenges and opportunities coexist. 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. This time, three engineers from NIO, Meng Tong, Chen Xi, and Wang Lulu, will share details of the technologies and architectures involved.
Watch this sharing session and you will learn:
1. Special requirements for model compilation and release in the field of autonomous driving
2. How to use TVM to perform collaborative optimization between different machine learning systems/ecosystems
3. Customized quantitative solutions designed for autonomous driving application scenarios
4. How to use the features of TVM to build a high-performance inference engine
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 will introduce our work on dynamic neural network compilation.
Watch this sharing session and you will learn:
1. The key to dynamic network compilation optimization: sub-tensor level data tracking
2. Better representation of dynamic neural networks
3. Dynamic compilation optimization opportunities in neural networks
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.
Active row:Scan the QR code to jump to the event registration
Baige Activities:Scan the QR code to jump to the Baige event registration
Scan the QR code and note "TVM Beijing" to join the event group
Considering the venue space of this event,We have only opened 100 places for you.It is recommended that you register as early as possible to secure your seat.
2023 Meet TVM series of events Q2 will be held in Beijing on June 17th, see you there!
This article was first published on HyperAI WeChat public platform~