From hand-tuned to generated: A reproducible Triton GPU kernel benchmark across different vendors

In the world of Large Language Models (LLMs), speed is very important. Much of this speed comes from highly specialized functions called GPU kernels which are small, focused routines that instruct the GPU how to perform calculations with the maximum efficiency....

Protecting Triton kernel deployments with cryptographic signatures

Triton is a domain-specific language and compiler for writing high-performance GPU kernels (snippets of compiled GPU code) using a Python-like syntax. It offers fine-grained control over memory and parallelism, making it ideal for custom, architecture-optimized...

Skip the JITters: Fast, trusted model kernels with OCI caching

Triton is a domain-specific language and compiler for writing high-performance GPU kernels in Python. It offers fine-grained control over memory and parallelism, making it ideal for custom, architecture-optimized compute in machine language and high-performance...

Welcome to Red Hat Emerging Technologies

Here you’ll find information about the emerging technology projects the Red Hat Office of the CTO is working on. For us, “emerging technologies” refers to those technologies that are still taking shape in the enterprise or even in research communities. Emerging technologies engineering is pre-product, purely upstream work. Not everything you see here will become part of the Red Hat portfolio roadmap, but we want to share this information with our customers and partners and encourage your participation. At Red Hat, we love to co-create with open source communities, partners and customers. We look forward to you engaging with us and providing your ideas and feedback on these projects.