Unverified50% confidenceFactExact time
Both parties have established a network topology for single-layer switching across 128 cards based on Ascend hardware, and claim it is scalable to larger clusters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/3/2026
First Seen
Valid until: 1/1/2027
Sources
Related Entities
Related Claims
UnverifiedThe wafer-scale engine enables all inter-core communication to be completed entirely on-chip, with memory bandwidth reaching tens of TB/s, far exceeding the cross-node bandwidth of GPU clusters.70% similarUnverifiedThe Ascend 950 single cabinet is equipped with 64 cards and 3,192 chips, the majority of which are switching chips responsible for managing inter-card data communication.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/970575API
curl https://kongchang.com/api/v1/knowledge/claims/970575MCP
get_claim(id=970575)