Post #2305

Hugging Face (Twitter) RT @RisingSayak: An ambitious project today 🔥 We got an agent to write custom kernels that actually work for a given model, hardware instruction set, and other relevant model-dependent constraints. Benchmarks are our rewards here 🤪 We got these kernels to work with Diffusers and `torch.compile` and they delivered ACTUAL SPEEDUP without messing up the quality 🏆 Despite the competitive landscape, we don't like to keep things private. Read all of it in the blog post below: https://huggingface.co/blog/custom-cuda-kernels-agent-skills