Andriy Oblivantsev
17592946fa
Revised `IPEXLLM_RELEASE_REPO` value and adjusted file and path references for consistency. Updated `docker-compose.yml` with refined environment variables, device mapping, restart policies, and added necessary port bindings for better functionality and maintainability.
65 lines
1.7 KiB
YAML
65 lines
1.7 KiB
YAML
services:
|
|
ollama-intel-gpu:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
IPEXLLM_RELEASE_REPO: ipex-llm/ipex-llm
|
|
IPEXLLM_RELEASE_VERSON: v2.2.0
|
|
IPEXLLM_PORTABLE_ZIP_FILENAME: ollama-ipex-llm-2.2.0-ubuntu.tgz
|
|
container_name: ollama-intel-gpu
|
|
restart: unless-stopped
|
|
devices:
|
|
# - /dev/dri:/dev/dri
|
|
- /dev/dri/renderD128:/dev/dri/renderD128
|
|
volumes:
|
|
- /tmp/.X11-unix:/tmp/.X11-unix
|
|
- ollama-intel-gpu:/root/.ollama
|
|
environment:
|
|
- ONEAPI_DEVICE_SELECTOR=level_zero:0
|
|
- IPEX_LLM_NUM_CTX=16384
|
|
- LD_LIBRARY_PATH:/opt/intel/oneapi/compiler/2024.2/lib
|
|
- DISPLAY=${DISPLAY}
|
|
- OLLAMA_DEFAULT_KEEPALIVE="6h"
|
|
- OLLAMA_HOST=0.0.0.0
|
|
- OLLAMA_KEEP_ALIVE=24h
|
|
- OLLAMA_MAX_LOADED_MODELS=1
|
|
- OLLAMA_MAX_QUEUE=512
|
|
- OLLAMA_MAX_VRAM=0
|
|
#- OLLAMA_NOHISTORY=false
|
|
#- OLLAMA_NOPRUNE=false
|
|
- OLLAMA_NUM_PARALLEL=1
|
|
|
|
ports:
|
|
- 11435:11434
|
|
|
|
ollama-webui:
|
|
image: ghcr.io/open-webui/open-webui:latest
|
|
container_name: ollama-webui
|
|
volumes:
|
|
- ollama-webui:/app/backend/data
|
|
depends_on:
|
|
- ollama-intel-gpu
|
|
ports:
|
|
- ${OLLAMA_WEBUI_PORT-3000}:8080
|
|
environment:
|
|
- OLLAMA_BASE_URL=http://ollama-intel-gpu:11434
|
|
- OLLAMA_DEFAULT_KEEPALIVE="6h"
|
|
#- OPENAI_API_BASE_URL=
|
|
#- OPENAI_API_KEY=
|
|
#
|
|
# AUTOMATIC1111_BASE_URL="http://localhost:7860"
|
|
|
|
- ENABLE_RAG_WEB_SEARCH=True
|
|
|
|
# DO NOT TRACK
|
|
- SCARF_NO_ANALYTICS=true
|
|
- DO_NOT_TRACK=true
|
|
- ANONYMIZED_TELEMETRY=false
|
|
extra_hosts:
|
|
- host.docker.internal:host-gateway
|
|
restart: unless-stopped
|
|
volumes:
|
|
ollama-webui: {}
|
|
ollama-intel-gpu: {}
|