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 #441] [MERGED] GGUF support #15421

New Issue
Closed
opened 2026-04-16 04:58:48 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 04:58:48 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/441
Author: @BruceMacD
Created: 8/29/2023
Status: ✅ Merged
Merged: 9/7/2023
Merged by: @BruceMacD

Base: main ← Head: brucemacd/gguf

📝 Commits (10+)

📊 Changes

10 files changed (+541 additions, -137 deletions)

View changed files

📝 .gitmodules (+8 -3)
📝 llm/ggml.go (+50 -31)
➕ llm/gguf.go (+385 -0)
📝 llm/llama.cpp/generate.go (+3 -1)
📝 llm/llama.cpp/generate_darwin_amd64.go (+3 -1)
📝 llm/llama.cpp/generate_darwin_arm64.go (+3 -1)
➕ llm/llama.cpp/gguf (+1 -0)
📝 llm/llama.go (+72 -94)
📝 llm/llm.go (+15 -5)
📝 server/images.go (+1 -1)

📄 Description

This change adds support for running GGUF models which are currently in beta with llama.cpp. We will continue to run GGML models and this transition will be seamless to users.

  • Adds a llama.cpp mainline submodule which runs GGUF models
  • Dynamically select the right runner for the model type
  • Moved a some code to different files
./ollama run gguf-codellama hello world

This is your first interaction with me. I am a bot, and I am created by you. Please ask me any questions you would like answered.

As mentioned in #423

🔄 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/441 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 8/29/2023 **Status:** ✅ Merged **Merged:** 9/7/2023 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `brucemacd/gguf` --- ### 📝 Commits (10+) - [`36bd33a`](https://github.com/ollama/ollama/commit/36bd33a63d65bfb0d83b98c780b379c70b937d5b) gguf support - [`f90a543`](https://github.com/ollama/ollama/commit/f90a5434b74b97d08eea5252e56fac247bccc3f8) pr feedback - [`5edf9b6`](https://github.com/ollama/ollama/commit/5edf9b6a4a01ccd2492f12bf26a495f44c314649) Delete model.go - [`1d904a9`](https://github.com/ollama/ollama/commit/1d904a99adfa0a8d3ac91662723ffdbbf8ecd410) remove unneeded function - [`a038d21`](https://github.com/ollama/ollama/commit/a038d21ed0f3e433d3ff497ec8f3e8e478736eb2) update gguf verison - [`f545015`](https://github.com/ollama/ollama/commit/f5450158ba268e4864e08b8bdd77f54dcf3c5f6b) refactor process lifecycle - [`5b2a258`](https://github.com/ollama/ollama/commit/5b2a2581670b0d3a33f3b521e8bb678409e3347c) update gguf decoder for v2 - [`6b407d8`](https://github.com/ollama/ollama/commit/6b407d88e793a916f9f51170f1d0a1e5d6f32382) s/mf/ggml/ - [`59aaf85`](https://github.com/ollama/ollama/commit/59aaf85b35d7efb10619c4fff18eeead97540002) disable gpu for q8_0 on ggml only - [`305c39a`](https://github.com/ollama/ollama/commit/305c39a315527be318ab43f5e146d2e3a084266a) shallow submodules ### 📊 Changes **10 files changed** (+541 additions, -137 deletions) <details> <summary>View changed files</summary> 📝 `.gitmodules` (+8 -3) 📝 `llm/ggml.go` (+50 -31) ➕ `llm/gguf.go` (+385 -0) 📝 `llm/llama.cpp/generate.go` (+3 -1) 📝 `llm/llama.cpp/generate_darwin_amd64.go` (+3 -1) 📝 `llm/llama.cpp/generate_darwin_arm64.go` (+3 -1) ➕ `llm/llama.cpp/gguf` (+1 -0) 📝 `llm/llama.go` (+72 -94) 📝 `llm/llm.go` (+15 -5) 📝 `server/images.go` (+1 -1) </details> ### 📄 Description This change adds support for running GGUF models which are currently in beta with llama.cpp. We will continue to run GGML models and this transition will be seamless to users. - Adds a llama.cpp mainline submodule which runs `GGUF` models - Dynamically select the right runner for the model type - Moved a some code to different files ``` ./ollama run gguf-codellama hello world This is your first interaction with me. I am a bot, and I am created by you. Please ask me any questions you would like answered. ``` As mentioned in #423 --- <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 2026-04-16 04:58:48 -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#15421
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?