At PyData NYC tutorial, by Jacob Tomlinson, I learned that now it is possible to access the same array on the GPU from pytorch and cupy. I'm loving how it will let you use the strengths of different libraries without dealing with extra memory copies.
https://nyc2024.pydata.org/cfp/talk/VAVRYW/
[#]PyDataNYC2024
[#]pytorch
[#]cupy
=> More informations about this toot | More toots from davidruffner@raphus.social
The PyData NYC 2024 talk videos are available online! https://www.youtube.com/playlist?list=PLGVZCDnMOq0ohEIZ-_wM2W_xqSVjyA3dC
Here is the link to the GPU acceleration in Python tutorial that I referenced above: https://youtu.be/Aumh3evLSKc?feature=shared
[#]PyDataNYC2024
[#]python
=> More informations about this toot | More toots from davidruffner@raphus.social
text/gemini
This content has been proxied by September (ba2dc).