Deliver an Ethernet based open, interoperable, high performance, full-communications stack architecture to meet the growing network demands of AI & HPC at scale






























Root Network












*Please note that not all members are displayed on this page.
NoLimit is an industry foundation for high-performance Ethernet used in AI and HPC. We convene operators, silicon vendors, and systems companies to keep Ethernet open, interoperable, and ready for scale-out clusters, without locking the industry to a single proprietary fabric.
Not on this site. Technical work happens inside the member working groups, and members receive documents directly. The public site is for the foundation’s mission, membership, and news.
AI and HPC need higher scale, higher bandwidth density, multipathing, and faster reaction to congestion. Ethernet already has the largest ecosystem and the best cost curve. NoLimit exists to close the remaining performance gaps without abandoning that ecosystem.
We work with SDOs and peer alliances, including OCP, SNIA, OpenFabrics, and IEEE 802.3, so NoLimit work can land in the broader Ethernet family rather than sitting beside it.
Any organization that builds or operates hardware or software for AI and HPC, or that wants to take advantage of Ethernet as it is extended for those workloads.
Yes. Steering, General, and Contributor. See the Membership page for benefits and how to apply.