github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #7138] [CLOSED] llama: wire up builtin runner #12323

New Issue
Closed
opened 2026-04-12 23:55:26 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:55:26 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7138
Author: @dhiltgen
Created: 10/8/2024
Status: ❌ Closed

Base: main ← Head: go_server_lcd_builtin

📝 Commits (1)

  • 923b329 llama: wire up builtin runner

📊 Changes

12 files changed (+64 additions, -18 deletions)

View changed files

📝 llama/make/Makefile.default (+3 -3)
📝 llama/make/gpu.make (+1 -1)
📝 llama/runner/cache.go (+1 -1)
📝 llama/runner/cache_test.go (+1 -1)
➕ llama/runner/cmd/cmd.go (+7 -0)
📝 llama/runner/requirements.go (+1 -1)
📝 llama/runner/runner.go (+3 -2)
📝 llama/runner/stop.go (+1 -1)
📝 llama/runner/stop_test.go (+1 -1)
📝 llm/server.go (+22 -6)
📝 main.go (+9 -0)
📝 runners/common.go (+14 -1)

📄 Description

This adds a new entrypoint into the ollama CLI to run the cgo built runner. On Mac arm64, this will have GPU support, but on all other platforms it will be the lowest common denominator CPU build. After we fully transition to the new Go runners more tech-debt can be removed and we can stop building the "default" runner via make and rely on the builtin always.

With this change, we achieve the clean build on MacOS ARM of being able to simply say

go build .
./ollama serve

...and run on the GPU. (No make or generate required.)

Replaces #6991 on main

🔄 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/7138 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 10/8/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `go_server_lcd_builtin` --- ### 📝 Commits (1) - [`923b329`](https://github.com/ollama/ollama/commit/923b3294817f9106c40e3dce050f5375141b8da1) llama: wire up builtin runner ### 📊 Changes **12 files changed** (+64 additions, -18 deletions) <details> <summary>View changed files</summary> 📝 `llama/make/Makefile.default` (+3 -3) 📝 `llama/make/gpu.make` (+1 -1) 📝 `llama/runner/cache.go` (+1 -1) 📝 `llama/runner/cache_test.go` (+1 -1) ➕ `llama/runner/cmd/cmd.go` (+7 -0) 📝 `llama/runner/requirements.go` (+1 -1) 📝 `llama/runner/runner.go` (+3 -2) 📝 `llama/runner/stop.go` (+1 -1) 📝 `llama/runner/stop_test.go` (+1 -1) 📝 `llm/server.go` (+22 -6) 📝 `main.go` (+9 -0) 📝 `runners/common.go` (+14 -1) </details> ### 📄 Description This adds a new entrypoint into the ollama CLI to run the cgo built runner. On Mac arm64, this will have GPU support, but on all other platforms it will be the lowest common denominator CPU build. After we fully transition to the new Go runners more tech-debt can be removed and we can stop building the "default" runner via make and rely on the builtin always. With this change, we achieve the clean build on MacOS ARM of being able to simply say ``` go build . ./ollama serve ``` ...and run on the GPU. (No make or generate required.) Replaces #6991 on main --- <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 2026-04-12 23:55:26 -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#12323
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?