Microsoft previews USB4 RDMA for distributed AI inference on Windows 11
Microsoft announced a developer preview of USB4-based RDMA that lets two or more compatible Windows 11 PCs pool memory and GPU capacity to run a shared AI model through supported inference frameworks, without dedicated RDMA adapters or switches. Microsoft reported round-trip latency of about 28–50 microseconds for small transfers. In separate vendor tests, Microsoft used three AMD mini PCs to run a four-bit-quantized 235-billion-parameter Qwen3 model at about 18.5 tokens per second; AMD reported about 22 tokens per second for Qwen3-235B-A22B, while Intel reported 54.2 tokens per second for GPT-OSS-120B on four Core Ultra Series 3 PCs.
The preview provides a USB4-based route for distributed local-AI inference across compatible Windows 11 systems without dedicated RDMA adapters or switches. The report also includes vendor-reported latency and model-throughput measurements, although test conditions differed and independent validation was not provided.
#Microsoft#Windows 11#AMD#Ryzen AI Max+ 395#Intel#Core Ultra Series 3#Qwen3#Qwen3-235B-A22B#GPT-OSS-120B