使用 Docker Compose 安装 Ollama 及模型

发表于 分类于

docker-compose.yaml

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
networks:
  ollama:
    external: true

services:
  ollama:
    image: ollama/ollama:0.4.1
    container_name: ollama
    restart: always
    networks:
      - ollama
    deploy:
      resources:
        reservations:
          # noinspection ComposeUnknownValues
          devices:
            - driver: nvidia
              capabilities: [ gpu ]
    environment:
      - OLLAMA_KEEP_ALIVE=24h
    volumes:
      - "${COMPOSE_DATA_DIR:-/data}/ollama/ollama:/root/.ollama"
    ports:
      - "11434:11434"

  ollama-webui:
    image: ghcr.io/open-webui/open-webui:0.3.35
    container_name: ollama-webui
    restart: always
    networks:
      - ollama
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
      - ENV=dev
      - WEBUI_AUTH=False
      - WHISPER_MODEL_AUTO_UPDATE=False
      - RAG_EMBEDDING_MODEL_AUTO_UPDATE=False
      - RAG_RERANKING_MODEL_AUTO_UPDATE=False
    volumes:
      - "${COMPOSE_DATA_DIR:-/data}/ollama/webui:/app/backend/data"
    ports:
      - "8080:8080"

拉取模型

  • https://ollama.com/library
  • https://ollama.com/library/qwen2.5
1
docker exec -it ollama bash
1
2
3
ollama list
ollama pull qwen2.5
ollama list

使用模型

打开 http://${IP}:8080 访问 webui，左上角选择模型 qwen2.5：

webui 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01              Driver Version: 565.57.01      CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  Tesla T4                       Off |   00000000:00:10.0 Off |                    0 |
| N/A   33C    P0             25W /   70W |    5255MiB /  15360MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
|   1  Tesla T4                       Off |   00000000:00:11.0 Off |                    0 |
| N/A   24C    P8              9W /   70W |       3MiB /  15360MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A    326540      C   ...unners/cuda_v12/ollama_llama_server       5252MiB |
+-----------------------------------------------------------------------------------------+