github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 16:36:54 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

[PR #12775] [MERGED] Fix vulkan PCI ID and ID handling #12683

New Issue
Closed
opened 2025-11-12 16:43:28 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-12 16:43:28 -06:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12775
Author: @dhiltgen
Created: 10/24/2025
Status: ✅ Merged
Merged: 10/28/2025
Merged by: @dhiltgen

Base: main ← Head: vulkan_indexes

📝 Commits (2)

📊 Changes

15 files changed (+418 additions, -447 deletions)

View changed files

📝 discover/runner.go (+20 -7)
📝 discover/types.go (+3 -0)
📝 llama/patches/0026-GPU-discovery-enhancements.patch (+352 -45)
📝 llama/patches/0027-NVML-fallback-for-unified-memory-GPUs.patch (+1 -1)
➖ llama/patches/0027-vulkan-get-GPU-ID-ollama-v0.11.5.patch (+0 -95)
📝 llama/patches/0028-CUDA-Changing-the-CUDA-scheduling-strategy-to-spin-1.patch (+1 -1)
➖ llama/patches/0028-vulkan-pci-and-memory.patch (+0 -254)
📝 llama/patches/0029-report-LoadLibrary-failures.patch (+0 -0)
📝 ml/backend/ggml/ggml.go (+3 -1)
📝 ml/backend/ggml/ggml/include/ggml-backend.h (+0 -3)
📝 ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu (+3 -12)
📝 ml/backend/ggml/ggml/src/ggml-impl.h (+1 -1)
📝 ml/backend/ggml/ggml/src/ggml-vulkan/ggml-vulkan.cpp (+17 -17)
📝 ml/backend/ggml/ggml/src/mem_hip.cpp (+11 -8)
📝 ml/device.go (+6 -2)

📄 Description

Intel GPUs may not report PCI IDs which was leading to incorrect overlap detection. Switch to using the existing PCI IDs, however AMD GPUs claim not to report PCI IDs, but actually do, so try anyway, as this is required for ADLX to find the GPUs on Windows.

Draft while I test on more systems...

🔄 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/12775 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 10/24/2025 **Status:** ✅ Merged **Merged:** 10/28/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `vulkan_indexes` --- ### 📝 Commits (2) - [`5c5fd1e`](https://github.com/ollama/ollama/commit/5c5fd1ebe84c9f1fae78426b3d58f2fe4c742c87) Fix vulkan PCI ID and ID handling - [`4420984`](https://github.com/ollama/ollama/commit/4420984c038687c904614e1f96af906b7fda43f9) review comments ### 📊 Changes **15 files changed** (+418 additions, -447 deletions) <details> <summary>View changed files</summary> 📝 `discover/runner.go` (+20 -7) 📝 `discover/types.go` (+3 -0) 📝 `llama/patches/0026-GPU-discovery-enhancements.patch` (+352 -45) 📝 `llama/patches/0027-NVML-fallback-for-unified-memory-GPUs.patch` (+1 -1) ➖ `llama/patches/0027-vulkan-get-GPU-ID-ollama-v0.11.5.patch` (+0 -95) 📝 `llama/patches/0028-CUDA-Changing-the-CUDA-scheduling-strategy-to-spin-1.patch` (+1 -1) ➖ `llama/patches/0028-vulkan-pci-and-memory.patch` (+0 -254) 📝 `llama/patches/0029-report-LoadLibrary-failures.patch` (+0 -0) 📝 `ml/backend/ggml/ggml.go` (+3 -1) 📝 `ml/backend/ggml/ggml/include/ggml-backend.h` (+0 -3) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu` (+3 -12) 📝 `ml/backend/ggml/ggml/src/ggml-impl.h` (+1 -1) 📝 `ml/backend/ggml/ggml/src/ggml-vulkan/ggml-vulkan.cpp` (+17 -17) 📝 `ml/backend/ggml/ggml/src/mem_hip.cpp` (+11 -8) 📝 `ml/device.go` (+6 -2) </details> ### 📄 Description Intel GPUs may not report PCI IDs which was leading to incorrect overlap detection. Switch to using the existing PCI IDs, however AMD GPUs claim not to report PCI IDs, but actually do, so try anyway, as this is required for ADLX to find the GPUs on Windows. ~~Draft while I test on more systems...~~ --- <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 2025-11-12 16:43:28 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
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-ollama#12683
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?