Commit Graph
64 Commits
Author SHA1 Message Date
eSliderandCursor 971852d3af Rework README for better GitHub presentation
Rewrite README with clear value proposition, architecture diagram,
troubleshooting section, and streamlined structure. Update CHANGELOG
to reflect full history of Vulkan-to-SYCL migration.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 17:31:33 +00:00
eSliderandCursor c56646e7e7 Switch GPU backend from Vulkan to SYCL for ~2x inference performance on Intel GPUs
Build ggml-sycl from upstream llama.cpp (commit a5bb8ba4, matching ollama's
vendored ggml) using Intel oneAPI 2025.1.1 in a multi-stage Docker build.
Patch two ollama-specific API divergences via patch-sycl.py: added batch_size
parameter to graph_compute, removed GGML_TENSOR_FLAG_COMPUTE skip-check that
caused all compute nodes to be bypassed.

Tested: gemma3:1b — 27/27 layers on GPU, 10.2 tok/s gen, 65.3 tok/s prompt eval.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 17:28:23 +00:00
eSliderandCursor 63c3b81292 Upgrade ollama from 0.9.3 (IPEX-LLM) to 0.15.6 (official) with Vulkan Intel GPU
Replace the IPEX-LLM portable zip (bundling a patched ollama 0.9.3 with SYCL)
with the official ollama 0.15.6 release using the Vulkan backend for Intel GPU
acceleration. The official ollama project does not ship a SYCL backend; Vulkan
is their supported path for Intel GPUs.

- Use official ollama binary with Vulkan runner (OLLAMA_VULKAN=1)
- Strip CUDA/MLX runners from image to save space
- Add mesa-vulkan-drivers for Intel ANV Vulkan ICD
- Remove all IPEX-LLM env vars and wrapper scripts
- Simplify entrypoint to /usr/bin/ollama serve directly
- Clean up docker-compose.yml: remove IPEX build args and env vars

Tested: Intel Arc Graphics (MTL) detected, 17/17 layers offloaded to Vulkan0
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 15:34:03 +00:00
eSliderandCursor 8debf2010b Fix ollama not reachable from host due to hardcoded OLLAMA_HOST in entrypoint
The IPEX-LLM bundled start-ollama.sh hardcodes OLLAMA_HOST=127.0.0.1 and
OLLAMA_KEEP_ALIVE=10m, overriding docker-compose environment variables and
preventing external connections through Docker port mapping.

- Add custom start-ollama.sh that honours env vars with sensible defaults
- Mount it read-only into the container
- Fix LD_LIBRARY_PATH env var syntax (: -> =)
- Add .gitignore for IDE/swap/webui data files
- Update CHANGELOG and README with fix documentation

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 15:18:37 +00:00
eSliderandCursor 96913a2a18 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>
2026-02-12 15:00:53 +00:00
eSlider 1239010eec Clean up Dockerfile by adding autoremove and autoclean commands to reduce image size 2025-06-21 00:37:38 +01:00
eSlider 0a7f974c04 Update Docker configurations and Intel GPU runtimes for improved performance 2025-06-21 00:35:20 +01:00
eSlider c98fd71fa2 Ignore shelf 2025-04-22 21:15:30 +01:00
eSlider 17592946fa Update Docker configurations for deployment improvements
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.
2025-04-22 17:56:04 +01:00
Matt CurfmanandGitHub 8172339ca5 Merge pull request #54 from blebo/update-ipex-v2.2.0
Update default to ipex-llm v2.2.0 (guide for v2.3.0-nightly in docs)
2025-04-19 17:00:06 -07:00
Matt CurfmanandGitHub dea2fd0afe Merge pull request #55 from charlescng/update_intel_libs
Update Intel libraries
2025-04-19 16:57:33 -07:00
Charles Ng f1bbedb599 Update Intel libraries 2025-04-18 01:51:10 +00:00
Adam Gibson 504a1d388f Update default to ipex-llm v2.2.0 (guide for v2.3.0-nightly in docs) 2025-04-16 21:25:38 +08:00
Matt CurfmanandGitHub 6964b45417 Merge pull request #50 from mattcurf/update_ipex
Update to ipex-llm-2.2.0b20250313
2025-03-17 12:17:44 -07:00
Matt Curfman 61288f5f6c Update to ipex-llm-2.2.0b20250313 2025-03-17 10:44:00 -07:00
Matt CurfmanandGitHub 86f07653dd Merge pull request #49 from blebo/dockerfile-args
Dockerfile ARGs to make it easier to use latest IPEX-LLM Ollama Portable Zip
2025-03-17 09:24:39 -07:00
Adam Gibson 451f91080c Revert compose to cached .tgz by default. 2025-03-17 19:29:53 +08:00
Adam Gibson b33c01f1f0 Updated README.md for Dockerfile args. 2025-03-16 16:56:50 +08:00
Adam Gibson 1e92fbe888 Updates to allow latest ollama in compose file, with fallback to cached in Dockerfile (if no build args provided) 2025-03-16 16:47:45 +08:00
Adam Gibson 2c82aed59c Update compose file with build args 2025-03-16 16:10:20 +08:00
Adam Gibson e1da4a4d16 Allow for user choice of ollama portable zip at build time 2025-03-16 15:37:06 +08:00
Matt CurfmanandGitHub d81b21c462 Merge pull request #42 from mattcurf/fix-links
Cache link
2025-02-22 20:51:12 -08:00
Matt Curfman 85e28fca19 Cache link 2025-02-22 20:27:34 -08:00
Matt CurfmanandGitHub db8d96c1a6 Merge pull request #39 from mattcurf/ollama_portable_zip 2025-02-21 22:31:41 -08:00
Matt Curfman fa579db492 Increase context window size 2025-02-19 15:26:01 -08:00
Matt CurfmanandGitHub fed3cf9ba0 Update README.md 2025-02-19 15:07:23 -08:00
Matt CurfmanandGitHub c47c879027 Merge branch 'main' into ollama_portable_zip 2025-02-19 15:04:19 -08:00
Matt Curfman dd84c202a7 Minor fixes 2025-02-19 15:00:46 -08:00
Matt Curfman 2fc526511f Update to use new ipex portable .zip packages 2025-02-19 14:56:56 -08:00
Matt CurfmanandGitHub ec7dec8f3b Merge pull request #36 from mattcurf/updated-docker-image
Update to latest ipex-llm dockerfile 20250211
2025-02-17 09:49:56 -08:00
Matt CurfmanandGitHub f08a310a2a Update README.md 2025-02-11 21:01:05 -08:00
Matt Curfman 765a8c09d7 Update to latest ipex-llm dockerfile 20250211 2025-02-11 20:40:41 -08:00
Matt CurfmanandGitHub 1581a505fb Merge pull request #27 from eltociear/patch-1
docs: update README.md
2025-02-04 20:40:12 -08:00
Ikko Eltociear AshimineandGitHub ddd565fc8d docs: update README.md
illlustrates -> illustrates
2025-01-31 02:09:53 +09:00
Matt CurfmanandGitHub c230c4518e Update README.md 2025-01-26 15:17:30 -08:00
Matt CurfmanandGitHub 8e69333f3f Update README.md 2025-01-26 15:14:29 -08:00
Matt CurfmanandGitHub d51c656e18 Merge pull request #24 from mattcurf/update-webui 2025-01-26 13:48:43 -08:00
Matt Curfman b74bab0b6a Update to latest open-webui releases 2025-01-23 17:28:33 -08:00
Matt CurfmanandGitHub 07e8a24b3a Merge pull request #21 from mattcurf/update_tags
Update ipex-llm image from Intel to 2.2.0-SNAPSHOT
2025-01-20 19:25:25 -08:00
Matt Curfman 6df0d8d3cc Update ipex-llm image from Intel to 2.2.0-SNAPSHOT 2025-01-16 22:00:31 -08:00
Matt CurfmanandGitHub 91d2045f7c Merge pull request #11 from mattcurf/ipex_intel_image
Update Dockerfile to use Intel public ipex container
2024-11-27 17:33:38 -08:00
Matt Curfman c74f6f2216 Update Dockerfile to use Intel public ipex container 2024-11-14 13:45:57 -08:00
Matt CurfmanandGitHub eb2389665f Merge pull request #8 from pepijndevos/patch-1 2024-11-07 22:34:00 -08:00
Pepijn de VosandGitHub 0e4cf4f154 Update docker-compose-wsl2.yml 2024-11-07 21:13:36 +01:00
Pepijn de VosandGitHub 2e18d91cd7 Update webui 2024-11-07 21:11:57 +01:00
Matt CurfmanandGitHub ff2a97961e Merge pull request #6 from mattcurf/fix_oneapi_dependency
Fix the ambiguous intel-basekit package in Dockerfile
2024-10-28 16:33:00 -07:00
Matt Curfman db0efa7eaf Fix the ambiguous intel-basekit package with specific version of oneAPI linked to by ipex-llm 2024-10-25 21:21:31 -07:00
Matt CurfmanandGitHub cff355161c Merge pull request #5 from eSlider/patch-1
Fix mess generation bug by updating libraries
2024-10-24 22:11:53 -07:00
eSliderandGitHub 6a39438666 Fix mess generation bug by updating libraries
* Level Zero 1.18.3
* IGC 1.0.17791
* Compute 24.39.31294.12

https://github.com/mattcurf/ollama-intel-gpu
2024-10-24 15:59:10 +01:00
Matt Curfman 40313a7364 Revert to ipex-llm version of ollama for gpu acceleration 2024-08-16 22:41:15 -07:00