github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #11160] Enable Intel GPU support with SYCL backend #44706

New Issue
Open
opened 2026-04-25 00:20:32 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 00:20:32 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11160
Author: @desmondsow
Created: 6/22/2025
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (10+)

📊 Changes

75 files changed (+22691 additions, -34 deletions)

View changed files

📝 .github/workflows/release.yaml (+50 -4)
📝 .github/workflows/test.yaml (+36 -2)
📝 CMakeLists.txt (+135 -7)
📝 CMakePresets.json (+13 -0)
📝 Dockerfile (+35 -3)
📝 app/ollama.iss (+12 -1)
📝 discover/gpu.go (+152 -10)
📝 discover/gpu_info.h (+1 -0)
➕ discover/gpu_info_sycl.c (+97 -0)
➕ discover/gpu_info_sycl.h (+29 -0)
📝 discover/gpu_linux.go (+9 -0)
➕ discover/gpu_sycl.go (+21 -0)
📝 discover/gpu_windows.go (+8 -0)
📝 discover/types.go (+6 -0)
📝 docs/development.md (+19 -0)
📝 docs/docker.md (+8 -0)
📝 envconfig/config.go (+3 -3)
➕ llama/patches/0021-catch-ggml-sycl-init-exception-to-prevent-crashing-w.patch (+41 -0)
📝 ml/backend/ggml/ggml/.rsync-filter (+1 -0)
➕ ml/backend/ggml/ggml/src/ggml-sycl/CMakeLists.txt (+185 -0)

...and 55 more files

📄 Description

This is a complete PR that enables Intel GPU support with the SYCL backend. It has been tested on both Ubuntu and Windows, using both integrated (iGPU) and discrete (dGPU) GPUs. The project can be built easily using the scripts/build_linux.sh and scripts/build_windows.ps1 scripts. For build environment setup, refer to docs/development.md.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/11160 **Author:** [@desmondsow](https://github.com/desmondsow) **Created:** 6/22/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (10+) - [`b6826bf`](https://github.com/ollama/ollama/commit/b6826bfe19fc4d356877298da39b1351008e5872) sync ggml-sycl from llama.cpp - [`741b91e`](https://github.com/ollama/ollama/commit/741b91e51af4cbe2183fe17c087a3d376516587c) add sycl support - [`166a864`](https://github.com/ollama/ollama/commit/166a864f4d4ceafff92f235d03ab1e34494562ea) add discover by sycl - [`f473711`](https://github.com/ollama/ollama/commit/f473711866380e52374bbd1f9782185e49941b33) compile with dpct - [`afa0777`](https://github.com/ollama/ollama/commit/afa0777f494c0f0a2dbec6d114fa22bfcbeedbbf) improve sycl discovery - [`d2fd672`](https://github.com/ollama/ollama/commit/d2fd672c2e7bdc678832f1bcd5765076b3b271f0) set UnreliableFreeMemory - [`92599f5`](https://github.com/ollama/ollama/commit/92599f5c53e39abd646a88bfa944cc531e0d8aa1) use sycl api by default - [`0fd78eb`](https://github.com/ollama/ollama/commit/0fd78eb32a750b8e77336ec5b72b08afccf5f45b) remove sycl_wrapper - [`387fb06`](https://github.com/ollama/ollama/commit/387fb06120779ddd62396f36b8ee5bbeefe825a1) add ci changes - [`28320d5`](https://github.com/ollama/ollama/commit/28320d5618b869d8d91ddae9d72afe62a50a79f1) add workflow_dispatch ### 📊 Changes **75 files changed** (+22691 additions, -34 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/release.yaml` (+50 -4) 📝 `.github/workflows/test.yaml` (+36 -2) 📝 `CMakeLists.txt` (+135 -7) 📝 `CMakePresets.json` (+13 -0) 📝 `Dockerfile` (+35 -3) 📝 `app/ollama.iss` (+12 -1) 📝 `discover/gpu.go` (+152 -10) 📝 `discover/gpu_info.h` (+1 -0) ➕ `discover/gpu_info_sycl.c` (+97 -0) ➕ `discover/gpu_info_sycl.h` (+29 -0) 📝 `discover/gpu_linux.go` (+9 -0) ➕ `discover/gpu_sycl.go` (+21 -0) 📝 `discover/gpu_windows.go` (+8 -0) 📝 `discover/types.go` (+6 -0) 📝 `docs/development.md` (+19 -0) 📝 `docs/docker.md` (+8 -0) 📝 `envconfig/config.go` (+3 -3) ➕ `llama/patches/0021-catch-ggml-sycl-init-exception-to-prevent-crashing-w.patch` (+41 -0) 📝 `ml/backend/ggml/ggml/.rsync-filter` (+1 -0) ➕ `ml/backend/ggml/ggml/src/ggml-sycl/CMakeLists.txt` (+185 -0) _...and 55 more files_ </details> ### 📄 Description This is a complete PR that enables Intel GPU support with the SYCL backend. It has been tested on both Ubuntu and Windows, using both integrated (iGPU) and discrete (dGPU) GPUs. The project can be built easily using the `scripts/build_linux.sh` and `scripts/build_windows.ps1` scripts. For build environment setup, refer to `docs/development.md`. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-25 00:20:32 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#44706
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?