Dear community:
We are glad to share that this summer, we will be building MLC, an open lecture series on machine learning compilation. As the field of machine learning compilation evolves, there has yet been a systematic material introducing this topic.
Because this is the first of its kind, there are still quite a few things to be explored together with the community. We will aim to share the lessons learnt through multiple years, and explore these topic together with the community.
Please checkout MLC | Home for a tentative outline and we welcome everyone to join us:)
TQ
Summary
Deploying innovative AI models in different production environments becomes a common problem as AI applications become more ubiquitous in our daily lives. Deployment of both training and inference workloads bring great challenges as we start to support a combinatorial choice of models and environment. Additionally, real world applications bring with a multitude of goals, such as minimizing dependencies, broader model coverage, leveraging the emerging hardware primitives for performance, reducing memory footprint, and scaling to larger environments.
Solving these problems for training and inference involves a combination of ML programming abstractions, learning-driven search, compilation, and optimized library runtime. These themes form an emerging topic – machine learning compilation that contains active ongoing developments. In this tutorials sequence, we offer the first comprehensive treatment of its kind to study key elements in this emerging field systematically. We will learn the key abstractions to represent machine learning programs, automatic optimization techniques, and approaches to optimize dependency, memory, and performance in end-to-end machine learning deployment.
Audience and Prerequisites
This course aims to target audiences who are working on machine learning in the wild. ML in practice is a broad topic that involves collaborations among multiple audiences, including machine learning scientists, machine learning engineers, and hardware providers.
The course requires a minimum set of prerequisites in data science and machine learning.
- Python, familiarity with numpy.
- Some background in one deep learning framework (e.g. PyTorch, TensorFlow, JAX)
- Experiences in system programming (e.g. C/CUDA) would be beneficial but not required.
This episode is a from-scratch introduction to TensorIR and should serve a good tutorial for anyone who is interested in some hands on experience to get started