Covering NVIDIA and domestic GPUs, large-model training, inference, and real-user services. Each case study independently presents the test background, environment, and results.
Deployments
Open a case study to see the environment, validation or delivery approach, and full results.
Using a coding inference service and comparing against traditional ROFT, this case validates that ZCube unlocks more effective inference compute through a flat fabric and more balanced network communication.
15%
Average GPU inference throughput increase
40.6%
Time to first token (TTFT) P99 reduction
33%
Network hardware cost reduction
In a domestic AI computing ecosystem, compare ZCube with traditional Clos across collective communication, training, and inference.
14.5%
All-to-All throughput increase
22%–30%
TTFT P99 reduction
7%–10%
Inference throughput increase
Compare ZCube with Clos and validate performance gains in collective communication, model training, and multi-tenant end-to-end inference.
119%
Collective communication performance increase
20.1%
Model-training throughput increase
11.5%
Inference latency reduction
A domestic thousand-GPU cluster has been live and stable for months, continuously carrying real traffic and serving real users.
Thousand-GPU scale
Domestic compute cluster deployed
Months
Stable production operation
Real users
Continuous service
Whether you are building a new cluster, upgrading an existing network, tuning performance, or deploying intelligent operations, we can assess how the network can unlock more effective compute.