TVM Stack: End to End Optimization for Deep Learning
Presenter: Tianqi Chen
https://homes.cs.washington.edu/~tqchen/
Tianqi Chen, one of the main authors of XGBoost and MXNet presents at the Seattle MXNet meetup on the TVM Stack.
The experimental results discussion is missing from the recording due to a technical issue. You can find the slides here:
https://cwiki.apache.org/confluence/download/attachments/75975742/TVM-MXNet-2.pdf?api=v2
Additional material presented during the event:
https://cwiki.apache.org/confluence/display/MXNET/Seattle
Intro Music: Catmosphere - Candy-Coloured Sky
Видео TVM Stack: End to End Optimization for Deep Learning канала Apache MXNet
https://homes.cs.washington.edu/~tqchen/
Tianqi Chen, one of the main authors of XGBoost and MXNet presents at the Seattle MXNet meetup on the TVM Stack.
The experimental results discussion is missing from the recording due to a technical issue. You can find the slides here:
https://cwiki.apache.org/confluence/download/attachments/75975742/TVM-MXNet-2.pdf?api=v2
Additional material presented during the event:
https://cwiki.apache.org/confluence/display/MXNET/Seattle
Intro Music: Catmosphere - Candy-Coloured Sky
Видео TVM Stack: End to End Optimization for Deep Learning канала Apache MXNet
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![New GPU Dependency Engine in Apache MXNet](https://i.ytimg.com/vi/Tlw_yTdr2bA/default.jpg)
![Matched-filtering Techniques and Deep Neural Networks for Gravitational Wave Astronomy](https://i.ytimg.com/vi/p-wocRl9Be0/default.jpg)
![Automatic Mixed Precision in Apache MXNet](https://i.ytimg.com/vi/_Pu5TpO5Ekw/default.jpg)
![The Apache Way](https://i.ytimg.com/vi/v1WLGIVS9yM/default.jpg)
![Standardizing on a single N-dimensional array API for Python](https://i.ytimg.com/vi/zWiOvfJfKKQ/default.jpg)
![Large Tensor Support](https://i.ytimg.com/vi/A1_snfrGeog/default.jpg)
![Using Apache MXNet in Production Deep Learning Streaming Pipelines](https://i.ytimg.com/vi/-GZjtHUNW58/default.jpg)
![Neural Time Series Models with GluonTS](https://i.ytimg.com/vi/83Qw9NDnxYs/default.jpg)
![Towards the ultimate framework efficiency](https://i.ytimg.com/vi/IMLXvg6gRFc/default.jpg)
![GluonCV with Apache MXNet](https://i.ytimg.com/vi/Xi_kUXsaQoI/default.jpg)
![Apache MXNet 2.0: Bridging Deep Learning and Machine Learning](https://i.ytimg.com/vi/z-bljNkXbZs/default.jpg)
![Optimizing Inference for Neural Machine Translation using Sockeye 2](https://i.ytimg.com/vi/lj_A1VtStJQ/default.jpg)
![AutoGluon: Powerful and Easy-to-use AutoML for Text, Image, and Tabular Data](https://i.ytimg.com/vi/UYW_gfZLFXE/default.jpg)
![Apache MXNet: A Call to ARMs](https://i.ytimg.com/vi/M9P7-V3l73I/default.jpg)
![Extending Apache MXNet for new features and performance](https://i.ytimg.com/vi/Fgbjj2vX88E/default.jpg)
![Serving 1 Million BERT inference requests for 20 cents](https://i.ytimg.com/vi/D5lUE-SSxY0/default.jpg)
![Optimizing inference on CPU in Apache MXNet 2.0](https://i.ytimg.com/vi/ojh4NOhmF2o/default.jpg)
![The History and the Future of Run-time Compilation in MXNet](https://i.ytimg.com/vi/KNldp4BAMF0/default.jpg)
![Looking for change? Roll the Dice and demand Attention](https://i.ytimg.com/vi/4D5VHWNLud4/default.jpg)
![CUDA Graphs support in Apache MXNet 1.8](https://i.ytimg.com/vi/z3m5rXG3EFY/default.jpg)
![Apache TVM and Machine Learing Compilation](https://i.ytimg.com/vi/fGQeOYhkrok/default.jpg)