AMD ROCm 6.0 is out, release notes: rocm.docs.amd.com/en/latest/abou…
🧮 Improved perf for lower precision math and attention layers
✨ Sparsity and quantization with DeepSpeed, ONNX-RT, CuPy plus new hipSPARSELt lib
🔥 Frameworks and ML pipeline updates for PyTorch, TensorFlow, JAX

📢 CuPy v13.0.0rc1 & 12.3.0 released! Support for cuTENSOR 2.0, distributed arrays, more cupyx.scipy.signal routines thanks to the cuSignal integration, and many other exciting features. Try the release candidate and let us know your feedback.
github.com/cupy/cupy/rele…

I had the rare opportunity to present @CuPy_team in front of Guido van Rossum Guido van Rossum. I've never thought I could have a chance to say 'Thank you for making Python!' to him directly. 😊

Thanks @PyConJapan guys for hosting & inviting me to #GuidoMeetup !

Exciting news from the CuPy team! 🙌 Improved interpolation & signal processing capabilities are bridging the gap between SciPy and CuPy. Performance gains are up 32x compared to SciPy's CPU implementations. CuPy v13.0 is approaching! 🚀 labs.quansight.org/blog/cupy-czi-…

Are you familiar with NumFOCUS? It's a non-profit that sponsors numpy, pandas, jupyter, Julia, scikit, matplotlib, and more. They've had decreased funding this year, let's help.
Donate to NumFOCUS today, and I will match all donations up to $10,000 within the next 48 hours!

🎉 CuPy has been approved for the Docker-Sponsored Open Source Program! A huge thank you to Docker Build Cloud is here! 🐳🧱☁️ for providing a free Docker Team subscription, empowering our community to thrive! 🙌
hub.docker.com/r/cupy/cupy

🎉 CuPy v12 is out now! This major release brings enhanced NumPy/SciPy API coverage, including the new SciPy interpolation module and ufunc methods. Also, you can now call Thrust/CUB from JIT kernels. Check out the blog to learn more about new features!
medium.com/cupy-team/rele…

Released CuPy v11.6.0/v12.0.0rc1, including more interpolation APIs and DLPack v0.8 support! Note that we are dropping Python 3.7 support in v12.
We plan to ship v12 final at the end of March, so try your app with this RC and share your feedback with us 🚀
github.com/cupy/cupy/rele…

CuPy v12.0.0b3/v11.5.0 released! CuPy now supports CUDA 12.0 and NVIDIA's latest H100 GPU. Check the release notes at: github.com/cupy/cupy/rele…

The ex-Chainer team at Preferred Networks has contributed a pluggable memory allocator feature in PyTorch required for our production use-case, and it comes with another bonus - making RAPIDS AI, CuPy, and many other CUDA-powered libraries interoperable with each other!

We have released CuPy v12.0.0b2 & v11.4.0! Added support for more routines in the SciPy interpolate package! Also, it is now possible to use NVIDIA’s CUB Reduction from the JIT. Check the release notes at:
github.com/cupy/cupy/rele…

Nice try, #ChatGPT 🙂

Today we are releasing CuPy v12.0.0b1/11.3.0. We add support for CUDA 11.8 & H100 GPUs, Python 3.11 and use of Thrust device functions in the JIT. Read the release notes at:
github.com/cupy/cupy/rele…

This is again a very impactful funding round. CZI Science has a major positive influence on open source scientific computing. From the EOSS grants, I'm particularly pleased to see CuPy and Spyder IDE getting their first ever grants, very much well-deserved! 🎉 1/3

🎖 We are pleased to announce that we have been awarded a grant from Chan Zuckerberg Initiative through the Essential Open Source Software for Science program!
medium.com/cupy-team/cupy…