As of last week, I am no longer at NVIDIA 🧵 Leaving the CUTLASS team was extremely hard. I will dearly miss my incredible colleagues and the extremely compelling mission statement of creating the world's best accelerator programming model w/ hardware software codesign 💚

Every GPU kernel writer in shambles

We have also heard the your feedback asking for better documentation. CuTe DSL documentation and all existing CUTLASS C++ documentation is now homed at docs.nvidia.com/cutlass with a fresh coat of paint!

We believe low level access to hardware is extremely important. High level generators rob away the freedom of programmers to experiment with new ideas and kernel designs while C++ is too slow to compile, learn, and debug. CuTe DSL provides the best of both worlds ⚡

This initial release ships with CuTe DSL, a programming language that is fully consistent with CuTe C++ in its programming model, APIs, abstraction level, and performance. Kernels in CuTe DSL look and feel like CuTe C++ but compile 100x faster without compromise in performance.

🚨🔥 CUTLASS 4.0 is released 🔥🚨 pip install nvidia-cutlass-dsl 4.0 marks a major shift for CUTLASS: towards native GPU programming in Python slidehelloworld.png docs.nvidia.com/cutlass/medi…

🔥🚨 CUTLASS Blackwell is here 🚨🔥 3.8 release is loaded with support for new features of Blackwell, even an attention kernel 👀 Go check it out here: github.com/nvidia/cutlass Can't wait to see what y'all end up cooking with this over the next few moths and years 💚

Even the text descriptions are using CuTe now to describe these layouts :D