Update Intel GPU stack and ipex-llm to latest available versions

- level-zero v1.22.4 -> v1.28.0
- IGC v2.11.7 -> v2.28.4
- compute-runtime 25.18.33578.6 -> 26.05.37020.3
- libigdgmm 22.7.0 -> 22.9.0
- ipex-llm ollama nightly 2.3.0b20250612 -> 2.3.0b20250725
- Docker compose: disable webui auth, stateless webui volume
- README formatting and GPU model update

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-02-12 15:00:53 +00:00
parent 1239010eec
commit 96913a2a18
4 changed files with 61 additions and 38 deletions
+27
View File
@@ -0,0 +1,27 @@
# Changelog
## 2026-02-12
### Updated Intel GPU runtime stack to latest releases
- **level-zero**: v1.22.4 -> v1.28.0
- Loader based on oneAPI Level Zero Specification v1.15.31
- Memory leak fixes, expanded multidriver teardown support
- **intel-graphics-compiler (IGC)**: v2.11.7 (build 19146) -> v2.28.4 (build 20760)
- Built with LLVM 16.0.6, opaque pointers support
- **compute-runtime**: 25.18.33578.6 -> 26.05.37020.3
- Built with IGC v2.28.4 and level-zero v1.27.0
- Panther Lake production support, Wildcat Lake pre-release
- **libigdgmm**: 22.7.0 -> 22.9.0
- **ipex-llm ollama** (nightly): 2.3.0b20250612 -> 2.3.0b20250725
- Latest available nightly Ubuntu ollama portable zip
### Docker Compose adjustments
- Disabled persistent webui volume for stateless restarts
- Disabled web UI authentication (`WEBUI_AUTH=False`)
### README
- Formatting and heading structure improvements
- Updated tested GPU model to Intel Core Ultra 5 155H
+12 -12
View File
@@ -11,23 +11,23 @@ RUN apt-get update && \
ocl-icd-libopencl1 && \
rm -rf /var/lib/apt/lists/*
# Intel GPU runtimes (release 25.18.33578.6)
# Intel GPU runtimes (release 26.05.37020.3)
RUN mkdir -p /tmp/gpu && cd /tmp/gpu && \
wget https://github.com/oneapi-src/level-zero/releases/download/v1.22.4/level-zero_1.22.4+u24.04_amd64.deb && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.11.7/intel-igc-core-2_2.11.7+19146_amd64.deb && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.11.7/intel-igc-opencl-2_2.11.7+19146_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.18.33578.6/intel-ocloc-dbgsym_25.18.33578.6-0_amd64.ddeb && \
wget https://github.com/intel/compute-runtime/releases/download/25.18.33578.6/intel-ocloc_25.18.33578.6-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.18.33578.6/intel-opencl-icd_25.18.33578.6-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.18.33578.6/libigdgmm12_22.7.0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/25.18.33578.6/libze-intel-gpu1_25.18.33578.6-0_amd64.deb && \
wget https://github.com/oneapi-src/level-zero/releases/download/v1.28.0/level-zero_1.28.0+u24.04_amd64.deb && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.28.4/intel-igc-core-2_2.28.4+20760_amd64.deb && \
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.28.4/intel-igc-opencl-2_2.28.4+20760_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/26.05.37020.3/intel-ocloc-dbgsym_26.05.37020.3-0_amd64.ddeb && \
wget https://github.com/intel/compute-runtime/releases/download/26.05.37020.3/intel-ocloc_26.05.37020.3-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/26.05.37020.3/intel-opencl-icd_26.05.37020.3-0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/26.05.37020.3/libigdgmm12_22.9.0_amd64.deb && \
wget https://github.com/intel/compute-runtime/releases/download/26.05.37020.3/libze-intel-gpu1_26.05.37020.3-0_amd64.deb && \
dpkg -i *.deb *.ddeb && rm -rf /tmp/gpu
# Install IPEX-LLM Portable Zip (ollama bundle v2.3.0-nightly)
RUN cd / && \
wget https://github.com/ipex-llm/ipex-llm/releases/download/v2.3.0-nightly/ollama-ipex-llm-2.3.0b20250612-ubuntu.tgz && \
tar xvf ollama-ipex-llm-2.3.0b20250612-ubuntu.tgz --strip-components=1 -C / && \
rm ollama-ipex-llm-2.3.0b20250612-ubuntu.tgz
wget https://github.com/ipex-llm/ipex-llm/releases/download/v2.3.0-nightly/ollama-ipex-llm-2.3.0b20250725-ubuntu.tgz && \
tar xvf ollama-ipex-llm-2.3.0b20250725-ubuntu.tgz --strip-components=1 -C / && \
rm ollama-ipex-llm-2.3.0b20250725-ubuntu.tgz
# Clean up any temporary files
RUN apt-get clean && \
+19 -23
View File
@@ -1,50 +1,46 @@
# ollama-intel-gpu
# Ollama for Intel GPU
[![GitHub license](https://img.shields.io/github/license/mattcurf/ollama-intel-gpu)](
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
> !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
## Prerequisites
* 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)
* Intel ARC series GPU (tested with Intel ARC A770 16GB and Intel(R) Core(TM) Ultra 5 155H integrated GPU)
# 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
Linux:
```bash
$ git clone https://github.com/mattcurf/ollama-intel-gpu
$ cd ollama-intel-gpu
$ docker compose up
## Linux
```shell
git clone https://github.com/mattcurf/ollama-intel-gpu
cd ollama-intel-gpu
docker compose up
```
*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.
> !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
## Update to the latest IPEX-LLM Portable Zip Version
### Update to the latest IPEX-LLM Portable Zip Version
To update to the latest portable zip version of IPEX-LLM's Ollama, update the compose file with the build arguments shown below, using the latest `ollama-*.tgz` release from https://github.com/intel/ipex-llm/releases/tag/v2.3.0-nightly , then rebuild the image.
```yaml
ollama-intel-gpu:
build:
context: .
dockerfile: Dockerfile
args:
IPEXLLM_RELEASE_REPO: intel/ipex-llm
IPEXLLM_RELEASE_VERSON: v2.3.0-nightly
IPEXLLM_PORTABLE_ZIP_FILENAME: ollama-ipex-llm-2.3.0b20250415-ubuntu.tgz
```
## References
# References
* https://dgpu-docs.intel.com/driver/client/overview.html
* https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md
* https://github.com/intel/ipex-llm/releases/download/v2.2.0-nightly/ollama-ipex-llm-2.2.0b20250313-ubuntu.tgz
+3 -3
View File
@@ -38,8 +38,8 @@ services:
ollama-webui:
image: ghcr.io/open-webui/open-webui:latest
container_name: ollama-webui
volumes:
- ollama-webui:/app/backend/data
#volumes:
# - ollama-webui:/app/backend/data
depends_on:
- ollama-intel-gpu
ports:
@@ -51,7 +51,7 @@ services:
#- OPENAI_API_KEY=
#
# AUTOMATIC1111_BASE_URL="http://localhost:7860"
- WEBUI_AUTH=False
- ENABLE_RAG_WEB_SEARCH=True
# DO NOT TRACK