Verified75% confidenceFactExact time
在H100 NVLink架构中，单台服务器内8块GPU可通过NVSwitch全互联，总带宽达900GB/s，相比PCIe 5.0的64GB/s有数量级提升
3
Sources
75%
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的双向带宽高达900GB/s，而传统PCIe总线带宽约为64GB/s83% similarUnverifiedNVLink 4.0（用于H100）单向带宽可达900 GB/s83% similarUnverifiedGB200 NVL72机柜将36块Grace CPU与72块Blackwell GPU通过NVLink 5.0互联，NVLink双向带宽为1.8 TB/s82% similarVerified英伟达NVLink芯片间高速互联带宽可达900GB/s以上，通过NVLink和NVSwitch构筑互联生态壁垒81% similarUnverified单台DGX H100服务器内8块GPU的双向带宽可达900GB/s80% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/461710API
curl https://kongchang.com/api/v1/knowledge/claims/461710MCP
get_claim(id=461710)