Verified90% confidenceFactExact time
In the H100 NVLink architecture, 8 GPUs within a single server can be fully interconnected via NVSwitch, achieving a total bandwidth of 900 GB/s, an order-of-magnitude improvement over PCIe 5.0's 64 GB/s.
8
Sources
90%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
TensorRT多设备推理：突破单GPU显存瓶颈的工程实践
rss6/25/2026
Related Claims
VerifiedNVLink 4.0 has a bidirectional bandwidth of up to 900 GB/s, while the bandwidth of a traditional PCIe bus is approximately 64 GB/s.83% similarVerifiedNVLink 4.0 (used in the H100) can achieve a unidirectional bandwidth of 900 GB/s.83% similarVerifiedNVIDIA's NVLink chip-to-chip high-speed interconnect bandwidth can reach over 900 GB/s, building an interconnect ecosystem barrier through NVLink and NVSwitch.81% similarUnverified单台DGX H100服务器内8块GPU的双向带宽可达900GB/s80% similarUnverifiedThe 8-GPU configuration of the HGX H200 interconnects 8 H200 GPUs with high bandwidth via NVLink and NVSwitch, with a total VRAM of up to 1.1 TB (HBM3e).79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/461710API
curl https://kongchang.com/api/v1/knowledge/claims/461710MCP
get_claim(id=461710)