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 #12333] feat: add support for MoE offloading #60484

New Issue
Open
opened 2026-04-29 15:28:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 15:28:34 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12333
Author: @Readon
Created: 9/18/2025
Status: 🔄 Open

Base: main ← Head: feat-moe-offload

📝 Commits (1)

  • fe7d9c5 feat: add support for MoE offloading

📊 Changes

5 files changed (+62 additions, -22 deletions)

View changed files

📝 api/types.go (+13 -11)
📝 docs/modelfile.md (+1 -0)
📝 llama/llama.go (+41 -6)
📝 llm/server.go (+2 -1)
📝 runner/llamarunner/runner.go (+5 -4)

📄 Description

This commit introduces a new parameter num_moe_offload to the Modelfile, allowing users to offload Mixture-of-Experts (MoE) weights to the CPU to reduce VRAM usage.

The num_moe_offload parameter can be set to:

  • A positive integer N to offload the first N MoE layers.
  • -1 to offload all MoE layers.
  • 0 (default) to disable offloading.

This is implemented by passing tensor override rules to the underlying llama.cpp library, which already supports this functionality. The documentation for the new parameter has also been updated.

Try to use Jules to solve the #11772

🔄 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/12333 **Author:** [@Readon](https://github.com/Readon) **Created:** 9/18/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feat-moe-offload` --- ### 📝 Commits (1) - [`fe7d9c5`](https://github.com/ollama/ollama/commit/fe7d9c5432ae1b2d805bb8c98411f18d520890a2) feat: add support for MoE offloading ### 📊 Changes **5 files changed** (+62 additions, -22 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+13 -11) 📝 `docs/modelfile.md` (+1 -0) 📝 `llama/llama.go` (+41 -6) 📝 `llm/server.go` (+2 -1) 📝 `runner/llamarunner/runner.go` (+5 -4) </details> ### 📄 Description This commit introduces a new parameter `num_moe_offload` to the Modelfile, allowing users to offload Mixture-of-Experts (MoE) weights to the CPU to reduce VRAM usage. The `num_moe_offload` parameter can be set to: - A positive integer `N` to offload the first `N` MoE layers. - `-1` to offload all MoE layers. - `0` (default) to disable offloading. This is implemented by passing tensor override rules to the underlying `llama.cpp` library, which already supports this functionality. The documentation for the new parameter has also been updated. Try to use Jules to solve the #11772 --- <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 2026-04-29 15:28:34 -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#60484
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?