Deploying DeepSeek in a Docker Environment

Prerequisites

The DeepSeek model weight file has been prepared.
Docker 24.0.0 or later has been installed and is running properly.
You have performed the operations in Configuring the Parameter Plane Network.

Restrictions

Currently, this operation is supported in a single-server Atlas 800I A3 SuperPoD Server system or single-server and two-node Atlas 800I A2 inference server (64 GB HCCS) systems.
Before deploying DeepSeek, configure the hccn_tool network for the target nodes. Refer to 1 to modify only the HCCN variable configuration area.

The following is a parameter configuration example. For a single-server system, enter information about the worker node. For a two-node system, enter information about two worker nodes and specify mindie_master. For details about the parameters, see Table 1 and Table 2.

[worker]
xx.xx.xx.77 ansible_ssh_user="******" ansible_ssh_pass="******"  
xx.xx.xx.87 ansible_ssh_user="******" ansible_ssh_pass="******." 

[all:vars]
mindie_master="xx.xx.xx.77"
weight_mount_path="/home/" # Weight mount directory, which is subsequently mounted to P/D instance containers. Ensure this directory contains the weight file.
model_weight_path="/home/whr/safetensor/" # Weight file path
cntr_mnt_path="/home/"
mindie_image_name="" 
mindie_image_file=""

**Table 1** [worker] parameters
Parameter	Required or Not	Description
IP	Yes	Server IP address. You can enter multiple IP addresses. The details are described as follows: index: sequence number of the server within the IP address segment, for example, 1.1.1.1-1.1.1.3 set_hostname="master-{index}", where 1.1.1.1 corresponds to set_hostname=master-1. The value is of the Int type. The default value is 1. step_len: IP address step. The last IP address is retained even if it is not within the step. For example, if 1.1.1.1-1.1.1.6 step_len=2 is set, 1.1.1.1,1.1.1.3,1.1.1.5,1.1.1.6 is output. Parameters can be parsed in the batch input configuration {}, including data calculation and conversion. After the parsing, the output is a character string. For example, if 1.1.1.1-1.1.1.3 set_hostname="master-{str(index+20)+'x'}" is entered, the parsed host information is 1.1.1.1 set_hostname="master-21x" .... The IP address segment parameters support only Python 3. When IPv6 is used, the IP address cannot be passed as a dynamic parameter.
ansible_ssh_user	Yes	Account for logging in to a remote server using SSH. The account must be root.
ansible_ssh_pass	No	Password for logging in to a remote server using SSH. If SSH key-based authentication is configured and the root user is allowed for login, you do not need to set this parameter.
ansible_ssh_port	No	Port for SSH connection. You do not need to set this parameter when the default port number 22 is used. If a non-default port is used, you need to configure this parameter.

**Table 2** [all:vars] parameters
Parameter	Required or Not	Description
weight_mount_path	Yes	Host directory mounted to a container. Example: /mnt/mindie_data/
model_weight_path	Yes	Path for accessing the weight file within a container. Example: /mnt/mindie_data/deepseek_diff_level/deepseek_r1_w8a8
mindie_image_name	No	Image name (name of the loaded MindIE image). Example: mindie:dev-2.0.RC1.B091-800I-A2-py311-ubuntu22.04-aarch64
mindie_image_file	No	Path to the image file in shared storage (MindIE image not loaded yet). Example: */mnt/weight/image/mindie_image.tar.gz**
cntr_mnt_path	Yes	Mount directory within a container, which is specified during container creation.
mindie_master	No This parameter is required in a two-node system.	IP address of the MindIE master node in a two-node system.

If a MindIE image exists in the cluster, configure mindie_image_name. If a MindIE image file exists on each node, configure mindie_image_file. Set either of the two parameters. If both are provided, mindie_image_name takes priority. If neither is provided, MindCluster Ascend Deployer will search for the image file in the ascend_deployer/resources/MindIE-image directory.
Ensure that the MindIE image corresponding to mindie_image_name and the image file corresponding to mindie_image_file exist in the cluster environment.

Parent topic: Configuring Server Installation and Deployment Parameters