Dr. T

CUDA Tile expands coverage to everyone's favorite language to use on their calculator. developer.nvidia.com/blog/cuda-tile…

New Drop. CUDA Tile team has optimizations of Flash Attention algorithms. The computational bottleneck of every transformer. 1.66x speedup on Blackwell. developer.nvidia.com/blog/tuning-fl…

🎉 We’re thrilled to announce the release of CuPy v14.0.0 — packed with new features, major performance boosts, important bug fixes, and more. ✅ Full compliance and support for NumPy v2 and Python Array API standard ✅ Support for CUDA pip wheels - much better installation footprint and interoperability with CUDA Python and PyTorch ✅ Support for structured dtypes & ML dtypes (starting with bfloat16) ✅ Better coverage over new NumPy & SciPy APIs ✅ Support for new cuFFT JIT callbacks - works on both Linux and Windows! ✅ New %gpu_timeit magic for Jupyter notebook users to properly benchmark GPU code This release marks the CuPy 10th anniversary, highlighting our close collaboration between @PreferredNet, and the wider open source community. @CuPy_Team 🥳 Accelerate your Python program on our GPUs.👇

Anyone who has spent an hour with a two toddlers year olds trying to avoid a nap, has no problem believing AI will be super intelligent in the next decade.

Asked Claude to give me a report on how one of my software projects is doing… I think it told me to get a new job.

Where should an over the hill programmer start building with Claude?

I was waiting this for a while and just did a toy project that generates cutile elementwise kernels based on torch export. it was fun

5 more stars until we hit 1000! Come on folks give a product owner some love =P github.com/nvidia/cutile-…

CUDA Tile is the future of GPU programming, and it's in Python. 🐍 cuTile Python in CUDA 13.1 lets you focus on your algorithm, not Tensor Core specifics. Simplify your HPC/AI code now. ✨ 🔗 nvda.ws/44LtUPJ

#SciPy2025 Announcing the launch of CCCL Python, a missing building block of heterogeneous programming in Python developer.nvidia.com/blog/deliverin…

Proud to support #PyConUS ➡️ us.pycon.org/2025/ Meet team in open spaces, summits, sprints & sessions: 🔹 Building transparent systems in Python 🔹 Scale smarter not harder with cuPyNumeric 🔹 Community-driven roadmap for Python packaging 🔹 GPU Programming in pure Python

Come see the CUDA Python team at PyCon in May!

🚀 Calling all CUDA developers! Whether you're a GPU programming newbie or a seasoned CUDA ninja, join our Meet Up! 📅 Jan 30, 5:30 PM PST 📍 Q Bay Center, 160 E Tasman Dr, San Jose, CA 🤝 Connect with the community and shape the future of CUDA. aicamp.ai/event/eventdet…

Excited to announce my new role on the Admin Board of NumFOCUS! Recently, I posted about our initial meeting on my personal blog. Check it out here: andy.terrel.us/blog/2025/01/1…

Obligatory new year's post: andy.terrel.us/blog/2025/01/0…

A peek into what we are building in CUDA Python! A full featured CUDA from our beloved Python. See @blelbach talk about NVIDIA pushing the boundary of Python performance. youtube.com/watch?v=86nMAR… See the code in action at github.com/aterrel/llm.py…

Hope to see all my old HPC friends at SC'24 in Atlanta next week. Will be presenting Monday, Nov 18 at the Workshop on Python. Come see as I outline the NVIDIA efforts to bring the entire CUDA Platform to the Python Ecosystem. hppss.github.io/SC24/schedule.…

.@pydatanyc , If you want to help shape the future of GPU computing, come chat with me at #pydatanyc2024! nyc2024.pydata.org/cfp/talk/TX3CB…

If you have 5 min, use Python and GPUs, my team would love to hear your thoughts on what areas we can help as the community adopts free threading. surveymonkey.com/r/FHF2RTL

After only a week of youtube, google, and chatgpt, I now have my neovim configured exactly how vim was set up. #thefutureisnow