llama : add simple option to enable CPU for MoE weights (--cpu-moe)#14992
Merged
llama : add simple option to enable CPU for MoE weights (--cpu-moe)#14992
Conversation
ggerganov
approved these changes
Jul 31, 2025
Contributor
|
Am I correct that this is on/off? It would be better to have an option for the number of layers (similar to -ngl). |
Member
Author
|
I am not convinced that it would be worth it. The goal here is to have a very simple option that works well enough for most people. If you want to min-max, you can still use the |
Contributor
|
Yes, I understand. And now I have an idea for my experiments :) |
Nexesenex
pushed a commit
to Nexesenex/croco.cpp
that referenced
this pull request
Aug 1, 2025
blime4
referenced
this pull request
in blime4/llama.cpp
Feb 5, 2026
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is intended to be a simple and curated way to use the CPU for the MoE weights. Internally, it is just setting up the appropriate tensor overrides, but this should be easier to use.