Home › Technologies › InfiniBand
InfiniBand
Technology
Networking
The low-latency training fabric NVIDIA acquired with Mellanox.
You're looking at a technology record: a building block of AI hardware — what it does, who makes it, and which chips and systems use it.
InfiniBand's RDMA transport, in-network reduction (SHARP) and lossless design made it the default scale-out network for big training clusters — Microsoft's OpenAI systems and thousands of others run Quantum-2 400 Gb/s fabrics, with 800 Gb/s Quantum-X families following. Its share is now contested by AI-tuned Ethernet, which costs less and has a broader vendor base.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Maintained by
Competes with
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.