Merge pull request #39 from mattcurf/ollama_portable_zip

2025-02-21 22:31:41 -08:00
parent ec7dec8f3b fa579db492
commit db8d96c1a6
4 changed files with 44 additions and 58 deletions
@@ -1,10 +1,32 @@
-FROM intelanalytics/ipex-llm-inference-cpp-xpu:latest
+FROM ubuntu:24.04
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=america/los_angeles

-RUN mkdir -p /llm/ollama; \
-    cd /llm/ollama; \
-    init-ollama;
-WORKDIR /llm/ollama
+# Base packages
+RUN apt update && \
+    apt install --no-install-recommends -q -y \
+    software-properties-common \
+    ca-certificates \
+    wget \
+    ocl-icd-libopencl1

-COPY commands.sh /llm/ollama/commands.sh
-RUN ["chmod", "+x", "/llm/ollama/commands.sh"]
-ENTRYPOINT ["/llm/ollama/commands.sh"]
+# Intel GPU compute user-space drivers
+RUN mkdir -p /tmp/gpu && \
+ cd /tmp/gpu && \
+ wget https://github.com/oneapi-src/level-zero/releases/download/v1.19.2/level-zero_1.19.2+u24.04_amd64.deb && \ 
+ wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.5.6/intel-igc-core-2_2.5.6+18417_amd64.deb && \
+ wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.5.6/intel-igc-opencl-2_2.5.6+18417_amd64.deb && \
+ wget https://github.com/intel/compute-runtime/releases/download/24.52.32224.5/intel-level-zero-gpu_1.6.32224.5_amd64.deb && \
+ wget https://github.com/intel/compute-runtime/releases/download/24.52.32224.5/intel-opencl-icd_24.52.32224.5_amd64.deb && \
+ wget https://github.com/intel/compute-runtime/releases/download/24.52.32224.5/libigdgmm12_22.5.5_amd64.deb && \
+ dpkg -i *.deb && \
+ rm *.deb
+
+# Install Ollama Portable Zip 
+RUN cd / && \
+  wget https://github.com/intel/ipex-llm/releases/download/v2.2.0-nightly/ollama-0.5.4-ipex-llm-2.2.0b20250218-ubuntu.tgz && \
+  tar xvf ollama-0.5.4-ipex-llm-2.2.0b20250218-ubuntu.tgz --strip-components=1 -C /
+
+ENV OLLAMA_HOST=0.0.0.0:11434
+
+ENTRYPOINT ["/bin/bash", "/start-ollama.sh"]
@@ -1,14 +1,18 @@
 # ollama-intel-gpu

-This repo illustrates the use of Ollama with support for Intel ARC GPU based via ipex-llm.  Run the recently released [deepseek-r1](https://github.com/deepseek-ai/DeepSeek-R1) model on your local Intel ARC GPU based PC using Linux or Windows WSL2.
+This repo illustrates the use of Ollama with support for Intel ARC GPU based via ipex-llm and Ollama Portable ZIP support.  Run the recently released [deepseek-r1](https://github.com/deepseek-ai/DeepSeek-R1) model on your local Intel ARC GPU based PC using Linux
+
+## Important Note
+
+All Ollama based ipex-llm defects should be reported directly to the ipex-llm project at https://github.com/intel/ipex-llm

 ## Screenshot
 ![screenshot](doc/screenshot.png)

 # Prerequisites
-* Ubuntu 24.04 or newer (for Intel ARC GPU kernel driver support. Tested with Ubuntu 24.04), or Windows 11 with WSL2 (graphics driver [101.5445](https://www.intel.com/content/www/us/en/download/785597/intel-arc-iris-xe-graphics-windows.html) or newer). 
-* 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)
+* Ubuntu 24.04 or newer (for Intel ARC GPU kernel driver support. Tested with Ubuntu 24.04.02
+* Installed Docker and Docker-compose tools
+* Intel ARC series GPU (tested with Intel ARC A770 16GB and Intel(R) Core(TM) Ultra 5 125H integrated GPU)
 
 # Usage

@@ -21,16 +25,10 @@ $ cd ollama-intel-gpu
 $ docker compose up 
 ```

-Windows WSL2:
-```bash
-$ git clone https://github.com/mattcurf/ollama-intel-gpu
-$ cd ollama-intel-gpu
-$ docker-compose -f docker-compose-wsl2.yml up 
-```
-
-*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.
+*Note:* If you have multiple GPU's installed (like integrated and discrete), set the ONEAPI_DEVICE_DELECTOR environment variable in the docker compose file to select the intended device to use.

 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://github.com/intel/ipex-llm/blob/main/docs/mddocs/DockerGuides/README.md)
+* https://dgpu-docs.intel.com/driver/client/overview.html
+* https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/ollama_portablze_zip_quickstart.md
@@ -1,35 +0,0 @@
-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
-      - /dev/dxg:/dev/dxg
-    volumes:
-      - /usr/lib/wsl:/usr/lib/wsl
-      - /tmp/.X11-unix:/tmp/.X11-unix
-      - ollama-intel-gpu:/root/.ollama
-    environment:
-      - DISPLAY=${DISPLAY}
-  ollama-webui:
-    image: ghcr.io/open-webui/open-webui
-    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
-    extra_hosts:
-      - host.docker.internal:host-gateway
-    restart: unless-stopped
-volumes:
-  ollama-webui: {}
-  ollama-intel-gpu: {}
@@ -10,7 +10,8 @@ services:
    volumes:
      - ollama-intel-gpu:/root/.ollama
    environment:
-      - DEVICE=Arc
+      - ONEAPI_DEVICE_SELECTOR=level_zero:0
+      - IPEX_LLM_NUM_CTX=16384
  ollama-webui:
    image: ghcr.io/open-webui/open-webui
    container_name: ollama-webui