github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #12679] [CLOSED] env config to bypass iGPUs #13915

New Issue
Closed
opened 2026-04-13 00:40:12 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:40:12 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12679
Author: @dhiltgen
Created: 10/17/2025
Status: ❌ Closed

Base: main ← Head: disable_igpu

📝 Commits (5)

  • 6f9d2cd DRY out the runner lifecycle code
  • 9621013 win: make incremental builds better
  • bf68164 Adjust sort order to consider iGPUs
  • 87655fb handle cpu inference oom scenarios
  • a58fa71 Add env var for iGPU disabling

📊 Changes

17 files changed (+794 additions, -981 deletions)

View changed files

📝 discover/cpu_linux_test.go (+0 -10)
📝 discover/gpu.go (+15 -149)
📝 discover/runner.go (+30 -140)
📝 discover/types.go (+0 -143)
📝 envconfig/config.go (+3 -3)
📝 llm/memory.go (+39 -23)
📝 llm/memory_test.go (+6 -14)
📝 llm/server.go (+216 -249)
📝 llm/server_test.go (+20 -19)
📝 ml/device.go (+215 -0)
📝 scripts/build_windows.ps1 (+15 -15)
📝 server/routes_debug_test.go (+21 -21)
📝 server/routes_generate_renderer_test.go (+21 -21)
📝 server/routes_generate_test.go (+33 -33)
📝 server/routes_harmony_streaming_test.go (+31 -31)
📝 server/sched.go (+77 -60)
📝 server/sched_test.go (+52 -50)

📄 Description

Putting this up as a draft in case we need a mechanism to allow users to entirely disable iGPUs once Vulkan is enabled in the official release.

(Carries #12540)

🔄 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/12679 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 10/17/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `disable_igpu` --- ### 📝 Commits (5) - [`6f9d2cd`](https://github.com/ollama/ollama/commit/6f9d2cd9fa68c51797245d0580d8c35f0b27189a) DRY out the runner lifecycle code - [`9621013`](https://github.com/ollama/ollama/commit/962101300ebc249318eae513ab0a3ce0ff54ca27) win: make incremental builds better - [`bf68164`](https://github.com/ollama/ollama/commit/bf68164c60d80f623f548b02d752b5a88bcb0cbe) Adjust sort order to consider iGPUs - [`87655fb`](https://github.com/ollama/ollama/commit/87655fb4edcaa9aa4c7eaaf35910040d6db0c508) handle cpu inference oom scenarios - [`a58fa71`](https://github.com/ollama/ollama/commit/a58fa71e084b34f89f95817cf64e3b0ec07d5855) Add env var for iGPU disabling ### 📊 Changes **17 files changed** (+794 additions, -981 deletions) <details> <summary>View changed files</summary> 📝 `discover/cpu_linux_test.go` (+0 -10) 📝 `discover/gpu.go` (+15 -149) 📝 `discover/runner.go` (+30 -140) 📝 `discover/types.go` (+0 -143) 📝 `envconfig/config.go` (+3 -3) 📝 `llm/memory.go` (+39 -23) 📝 `llm/memory_test.go` (+6 -14) 📝 `llm/server.go` (+216 -249) 📝 `llm/server_test.go` (+20 -19) 📝 `ml/device.go` (+215 -0) 📝 `scripts/build_windows.ps1` (+15 -15) 📝 `server/routes_debug_test.go` (+21 -21) 📝 `server/routes_generate_renderer_test.go` (+21 -21) 📝 `server/routes_generate_test.go` (+33 -33) 📝 `server/routes_harmony_streaming_test.go` (+31 -31) 📝 `server/sched.go` (+77 -60) 📝 `server/sched_test.go` (+52 -50) </details> ### 📄 Description Putting this up as a draft in case we need a mechanism to allow users to entirely disable iGPUs once Vulkan is enabled in the official release. (Carries #12540) --- <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 2026-04-13 00:40:12 -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#13915
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?