If you're looking to leverage the insane power of modern GPUs for data science and ML, you might think you'll need to use some low-level programming language such as C++. But the folks over at NVIDIA have been hard at work building Python SDKs which provide nearly native level of performance when doing Pythonic GPU programming. Bryce Adelstein Lelbach is here to tell us about programming your GPU in pure Python. 
 
Episode sponsors 
 
<a href='https://talkpython.fm/ppm'>Posit</a>
<a href='https://talkpython.fm/agntcy'>Agntcy</a>
<a href='https://talkpython.fm/training'>Talk Python Courses</a> 
 
<h2 class="links-heading">Links from the show</h2>
<div>Bryce Adelstein Lelbach on Twitter: <a href="https://x.com/blelbach?lang=en&featured_on=talkpython" target="_blank" >@blelbach</a> 
 
Episode Deep Dive write up: <a href="https://talkpython.fm/blog/posts/deep-dive-retrospective-at-talk-python/" target="_blank" >talkpython.fm/blog</a> 
 
NVIDIA CUDA Python API: <a href="https://github.com/NVIDIA/cuda-python?featured_on=talkpython" target="_blank" >github.com</a> 
Numba (JIT Compiler for Python): <a href="https://numba.pydata.org/?featured_on=talkpython" target="_blank" >numba.pydata.org</a> 
Applied Data Science Podcast: <a href="https://adspthepodcast.com?featured_on=talkpython" target="_blank" >adspthepodcast.com</a> 
NVIDIA Accelerated Computing Hub: <a href="https://github.com/NVIDIA/accelerated-computing-hub?featured_on=talkpython" target="_blank" >github.com</a> 
NVIDIA CUDA Python Math API Documentation: <a href="https://docs.nvidia.com/cuda/nvmath-python?featured_on=talkpython" target="_blank" >docs.nvidia.com</a> 
CUDA Cooperative Groups (CCCL): <a href="https://nvidia.github.io/cccl/cuda_cooperative/?featured_on=talkpython" target="_blank" >nvidia.github.io</a> 
Numba CUDA User Guide: <a href="https://nvidia.github.io/numba-cuda/user/kernels.html#introduction" target="_blank" >nvidia.github.io</a> 
CUDA Python Core API: <a href="https://nvidia.github.io/cuda-python/cuda-core?featured_on=talkpython" target="_blank" >nvidia.github.io</a> 
Numba (JIT Compiler for Python): <a href="https://numba.pydata.org/?featured_on=talkpython" target="_blank" >numba.pydata.org</a> 
NVIDIA’s First Desktop AI PC ($3,000): <a href="https://arstechnica.com/ai/2025/01/nvidias-first-desktop-pc-can-run-local-ai-models-for-3000/?featured_on=talkpython" target="_blank" >arstechnica.com</a> 
Google Colab: <a href="https://colab.research.google.com/?featured_on=talkpython" target="_blank" >colab.research.google.com</a> 
Compiler Explorer (“Godbolt”): <a href="https://godbolt.org/?featured_on=talkpython" target="_blank" >godbolt.org</a> 
CuPy: <a href="https://github.com/cupy/cupy?featured_on=talkpython" target="_blank" >github.com</a> 
RAPIDS User Guide: <a href="https://docs.rapids.ai/user-guide/?featured_on=talkpython" target="_blank" >docs.rapids.ai</a> 
Watch this episode on YouTube: <a href="https://www.youtube.com/watch?v=57POBhLVbcc" target="_blank" >youtube.com</a> 
Episode #509 deep-dive: <a href="https://talkpython.fm/509#takeaways-anchor" target="_blank" >talkpython.fm/509</a> 
Episode transcripts: <a href="https://talkpython.fm/episodes/transcript/509/gpu-programming-in-pure-python" target="_blank" >talkpython.fm</a> 
 
--- Stay in touch with us --- 
Subscribe to Talk Python on YouTube: <a href="https://talkpython.fm/youtube" target="_blank" >youtube.com</a> 
Talk Python on Bluesky: <a href="https://bsky.app/profile/talkpython.fm" target="_blank" >@talkpython.fm at bsky.app</a> 
Talk Python on Mastodon: <a href="https://fosstodon.org/web/@talkpython" target="_blank" >talkpython</a> 
Michael on Bluesky: <a href="https://bsky.app/profile/mkennedy.codes?featured_on=talkpython" target="_blank" >@mkennedy.codes at bsky.app</a> 
Michael on Mastodon: <a href="https://fosstodon.org/web/@mkennedy" target="_blank" >mkennedy</a> </div>

Podurama

Home

Trending

Personal

Your Podcasts

New Episodes

My Files

Favourite Episodes

Tags (Folders)

Recently Played

Bookmarks

Followed Playlists

#509: GPU Programming in Pure Python

Talk Python To Me

AI Chapters

AI Insights

Reviews