Cloud

CloudClustersasia-inference

asia-inference

scaling

ap-southeast-1 • NVIDIA L40S • Created 10/5/2026

GPU Utilization

89%

Memory Util.

76%

VRAM Usage

292 / 384 GB

Queue Depth

47

Node Count

2

Monthly Cost

$12,800.00

Network Configuration

VPC CIDR
10.3.0.0/16
Subnet
10.3.1.0/24
Private Endpoint
https://asia.osi-cloud.internal:8443

Scaling Configuration

Total GPUs
8
Total Nodes
2

Deployed Models

NameModelReplicasGPU Alloc.Latency (P50/P99)RPMTokens TodayStatus
deepseek-v4-pro-asiaDeepSeek V4 Pro44198ms / 520ms1.8K62.3M
scaling