Use VPC to accelerate the pulling of AI container images - Container Compute Service

Alibaba Cloud Container Compute Service (ACS) container images provide standard Internet services. When you start tasks in ACS, you need to pull images through the public network, which requires a period of time. Currently, ACS provides IN-VPC image access services. We recommend that you use the IN-VPC method to accelerate the pulling of AI container images.

Scenarios

Applicable scenarios

Applicable to all ACS environments (non-ACS environments do not support IN-VPC).
Applicable to scenarios where pods are directly created using the ACS console (by selecting from the artifact center page of the workload page, or by referencing images in YAML files).

Inapplicable scenarios

Pull AI container images through the public network in inapplicable scenarios.

How to use

Scope of use

All existing and new ACS AI container images in the egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun repository support IN-VPC pulling.

Usage method

To speed up image pulls from within your virtual private cloud (VPC), replace the standard image asset URI with a region-specific VPC endpoint.

Change the image path from this format:
egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/{image:tag}

To this format:
acs-registry-vpc.{region-id}.cr.aliyuncs.com/egslingjun/{image:tag}

{region-id}: The ID of the region where your ACS service is deployed. Examples: cn-beijing, cn-wulanchabu.
{image:tag}: The name and tag of the target AI container image. Examples: inference-nv-pytorch:25.10-vllm0.11.0-pytorch2.8-cu128-20251028-serverless and training-nv-pytorch:25.10-serverless.

Example

Asset URI of the previous AI container image pulled through the public network:

egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/training-nv-pytorch:25.10-serverless

Replace with the new AI container image asset URI that supports IN-VPC:

# Use ACS in the China (Beijing) region.
acs-registry-vpc.cn-beijing.cr.aliyuncs.com/egslingjun/training-nv-pytorch:25.10-serverless

# Use ACS in the China (Ulanqab) region.
acs-registry-vpc.cn-wulanchabu.cr.aliyuncs.com/egslingjun/training-nv-pytorch:25.10-serverless

Note

The egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/{image:tag} image can still be pulled over the public network.