Unverified50% confidenceFactExact time
Maia 300's scale-up network runs a custom AI transport over Ethernet, with a two-tier topology: an intra-rack half-switch architecture electrically connects all 96 accelerators, and a second optical tier connects up to 128 racks into a single superpod (12,288 accelerators).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedMaia 300 accelerators can connect to remote peers in the superpod at speeds of 750GB/s.72% similarUnverifiedThe Maia 300 rack contains 96 accelerators, draws 167 kilowatts, has 27.7TB of HBM capacity, and 1.7PB/s of aggregate memory bandwidth.67% similarUnverifiedBoth 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.67% similarUnverifiedThe 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1039913API
curl https://kongchang.com/api/v1/knowledge/claims/1039913MCP
get_claim(id=1039913)