Event Review | The Coordinated Development of Computing, Network, Software, Algorithm and Ecology, 2024 Meet AI Compiler Concluded Successfully!
On December 28, Shanghai had entered early winter, but the cold weather could not dampen everyone's enthusiasm. The venue was packed with people and the atmosphere of communication was strong. From industry challenges to technological innovation, from application scenarios to implementation results, the lecturers and the audience had a profound "Huashan Sword Contest" around the AI compiler.
Follow the WeChat public account "HyperAI Super Neural Network" and reply to the keyword "1228 AI Compiler" in the background to get the complete PPT of the guest.
This Meetup was divided into two sessions. In the technical sharing session, four senior compiler experts from Horizon Robotics, Zhiyuan, ByteDance, and Lingchuan Technology demonstrated the latest research results of their respective teams. They also combined rich practical application cases to explain in an easy-to-understand manner the application process and effects of these results in solving practical problems.
From the innovative design of compiler architecture, to performance optimization strategies in specific scenarios, to integrated applications with other technologies, the lecturers’ sharing covered many key aspects in the compiler field, providing participants with profound industry observations and valuable implementation experience.
In the roundtable session, Feng Siyuan, a Ph.D. from Shanghai Jiao Tong University and PMC of Apache TVM, served as the moderator. He and four lecturers focused on the core theme of "coordinated development of computing-network-software-algorithm-ecology" and launched a full-scale and multi-dimensional exchange of views. The audience also actively participated in the interaction, expressed their own insights, and exchanged ideas with the lecturers.
Event content review
The following is a brief introduction to the sharing content and a video review of the event.
Share topic:Transformer model compilation and deployment optimization practice
Contents:In recent years, the Transformer model has not only achieved remarkable results in the field of LLM, but has also been widely used in the field of computer vision. In the scenario of autonomous driving, the compilation and deployment optimization of the Transformer model is a complex process. The end-to-end model and VLM pose great challenges to the compilation optimization and deployment of the end side. This sharing mainly introduces some practices and experiences of Horizon in this regard.
Watch this sharing session and you will learn:
1. Challenges in Compilation, Optimization, and Deployment of Visual Transformer Models
2. Horizon's exploration and practice in Transformer model compilation optimization
Share Video:
https://www.bilibili.com/video/BV1wN6pYgEyi/?spm_id_from=333.999.0.0
Share topic:FlagGems: R&D progress and ecological application exploration
Contents:Since the release of version 2.0, with the close collaboration of the Zhiyuan team, partner manufacturers and the Triton China community, FlagGems has achieved significant R&D breakthroughs in the number of supported operators, computing performance, code generation, and runtime mechanisms. At the same time, FlagGems connects the upstream and downstream of the field, and has launched innovative explorations in large model training and reasoning adaptation, multi-backend chip integration, and other aspects, further expanding the application scenarios of operator libraries in a diverse ecosystem.
Watch this sharing session and you will learn:
1. FlagGems’ latest research and development achievements and technological advancements
2. Innovative practices and experiences in adapting operator libraries to large models
3. Technical solutions and application effects of multi-backend chip integration
4. Progress of Triton China Community and Diversified Ecosystem Construction
Share Video:
https://www.bilibili.com/video/BV1Le6JYXEuR/?spm_id_from=333.999.0.0
Share topic:AI compiler design from the perspective of computation-memory access-communication optimization
Contents:Compilation optimization for AI chips faces optimization challenges from three perspectives: computing, memory access, and communication. This report will share AI compiler design and optimization experience from three perspectives. From the computing perspective, we will share optimization for customized acceleration units; from the memory access perspective, we will share memory access modeling and optimization for AI chips; from the communication perspective, we will share experience and progress in computing and communication fusion.
Watch this sharing session and you will learn:
1. A global perspective on AI compiler optimization
2. Learn the experience and skills to fully utilize the computing power of AI chips
3. Understand the future development direction of distributed AI compilers
Share Video:
https://www.bilibili.com/video/BV1vX6EYDEkm/?spm_id_from=333.999.0.0
2025 Meet AI Compiler · Stay tuned
In 2023-2024, we successfully held 6 offline meetups in Beijing, Shanghai, and Shenzhen, gathering thousands of senior practitioners and enthusiasts, and gradually established a rich community ecosystem. In 2025, we will continue to develop the AI Compiler city map, and sincerely invite all companies and community partners to participate in co-creation in various forms, whether it is recommending lecturers or providing venues and coffee breaks, we welcome them very much~
Let's work together to create the most active AI compiler community in China! Finally, let's share a group photo of the scene❤️
Organizers and partners
HyperAI is a leading artificial intelligence and high-performance computing community in China.It aims to help developers and enthusiasts in China's data science and artificial intelligence industry learn, understand and practice by providing various infrastructures such as accelerated data set downloads, online tutorial demonstrations, in-depth interpretation of papers, and top conference calendar integration, and build the future of artificial intelligence with the community. Currently, the official website of Super Neuro has launched thousands of classic and high-quality public data sets and tutorials, and operates the most active AI compiler community in China.
Visit the official website:https://hyper.ai/
OpenBayes Bayesian Computing is a leading high-performance computing service provider in ChinaBy grafting classic software ecosystems and machine learning models onto new-generation heterogeneous chips, it provides industrial enterprises and university scientific research with faster and easier-to-use data science computing products. Its products have been adopted by dozens of large industrial scenarios or leading scientific research institutes.
Visit the official website:https://openbayes.com/
The MLC.AI community was established in June 2022. Chen Tianqi, the main inventor of Apache TVM and a well-known young scholar in the field of machine learning, led the team to launch 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 documentation was launched and successfully hosted on the HyperAI official website, further providing domestic developers interested in machine learning compilation with the basic settings for accessing and learning a new technology - documentation.
MLC Online Courses:https://mlc.ai/
TVM Chinese Documentation:https://tvm.hyper.ai/
Shanghai Wujiaochang Innovation and Entrepreneurship College is a non-profit education and service organization jointly initiated by the Yangpu District Government, famous universities, industry leading enterprises, and entrepreneurship service institutions. With the mission of "creating deep connections to make innovation and entrepreneurship more successful", it connects entrepreneurs and enablers, improves the allocation efficiency of dual innovation and entrepreneurship factor resources, and promotes creation.
In November 2022, the Wujiaochang Entrepreneurship Academy will officially open the academy's public space, opening up 800 square meters of space to the entrepreneurship and innovation crowd. It will also jointly launch the entrepreneurship and innovation charity brand "Academy Coffee" with partners such as CUHK Shanghai Center and Shui On Group, and invite KOLs, enterprises and social organizations that have a consensus on entrepreneurship and innovation charity services to become "charity partners" to jointly design different forms of ways for entrepreneurs to gather. So far, "Academy Coffee" has held 140+ entrepreneurship and innovation themed activities of different forms, bringing together 3,000+ participants.
Event Support
Get the PPT:Follow the WeChat public account "HyperAI Super Neural Network", reply to the keyword "1228 AI Compiler" in the background, and get the complete PPT of the guest.
Scan the QR code and remark "AI Compiler" to join the event group
