Merge pull request #36 from mattcurf/updated-docker-image

Update to latest ipex-llm dockerfile 20250211

Dockerfile

@@ -1,12 +1,10 @@
-FROM intelanalytics/ipex-llm-inference-cpp-xpu:2.2.0-SNAPSHOT
-
-ENV ZES_ENABLE_SYSMAN=1
-ENV OLLAMA_HOST=0.0.0.0:11434
+FROM intelanalytics/ipex-llm-inference-cpp-xpu:latest
 
 RUN mkdir -p /llm/ollama; \
     cd /llm/ollama; \
     init-ollama;
-
 WORKDIR /llm/ollama
 
-ENTRYPOINT ["./ollama", "serve"]
+COPY commands.sh /llm/ollama/commands.sh
+RUN ["chmod", "+x", "/llm/ollama/commands.sh"]
+ENTRYPOINT ["/llm/ollama/commands.sh"]

README.md

@@ -10,8 +10,6 @@ This repo illustrates the use of Ollama with support for Intel ARC GPU based via
 * Installed Docker and Docker-compose tools (for Linux) or Docker Desktop (for Windows)
 * Intel ARC series GPU. Tested with Intel ARC A770 16GB, Intel(R) Core(TM) Ultra 5 125H integrated GPU (Meteor Lake), and Intel(R) Core(TM) Intel Ultra 7 258V integrated GPU (Lunar Lake)
 
-*Note:* This branch uses the upstream ipex container published by Intel.  See the alternate branch [alternate_base_image](https://github.com/mattcurf/ollama-intel-gpu/tree/alternate_base_image) for an equivalent Dockerfile which builds everything from the published packages directly.
-
 # Usage
 
 The following will build the Ollama with Intel ARC GPU support, and compose those with the public docker image based on OpenWEB UI from https://github.com/open-webui/open-webui
@@ -30,13 +28,9 @@ $ cd ollama-intel-gpu
 $ docker-compose -f docker-compose-wsl2.yml up 
 ```
 
-*Note:* you will see the following message.  This is expected and harmless, as the docker image 'ollama-intel-gpu' is built locally.
-```
-ollama-intel-gpu Warning pull access denied for ollama-intel-gpu, repository does not exist or may require 'docker login': denied: requested access to the resource is denied
-```
+*Note:* ipex-llm now requires setting the GPU type in the docker-compose.yml file.  Set variable DEVICE= to 'Arc' or 'iGPU'.  See https://github.com/intel/ipex-llm/blob/main/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md for more information.
 
 Then launch your web browser to http://localhost:3000 to launch the web ui.  Create a local OpenWeb UI credential, then click the settings icon in the top right of the screen, then select 'Models', then click 'Show', then download a model like 'llama3.1:8b-instruct-q8_0' for Intel ARC A770 16GB VRAM
 
 # References
-* https://dgpu-docs.intel.com/driver/client/overview.html
-* https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/ollama_quickstart.html
+* [https://dgpu-docs.intel.com/driver/client/overview.html](https://github.com/intel/ipex-llm/blob/main/docs/mddocs/DockerGuides/README.md)

commands.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+source ipex-llm-init --gpu --device $DEVICE
+export OLLAMA_HOST=0.0.0.0:11434
+cd /llm/ollama
+./ollama serve

docker-compose.yml

@@ -1,19 +1,16 @@
-version: "3.9"
 services:
   ollama-intel-gpu:
     build:
       context: .
       dockerfile: Dockerfile
     container_name: ollama-intel-gpu
-    image: ollama-intel-gpu:latest
     restart: always
     devices:
       - /dev/dri:/dev/dri
     volumes:
-      - /tmp/.X11-unix:/tmp/.X11-unix
       - ollama-intel-gpu:/root/.ollama
     environment:
-      - DISPLAY=${DISPLAY}
+      - DEVICE=Arc
   ollama-webui:
     image: ghcr.io/open-webui/open-webui
     container_name: ollama-webui