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

[GH-ISSUE #10630] Update llama.cpp to include new optimizations for MoE models on Apple Silicon #6993

New Issue
Closed
opened 2026-04-12 18:53:14 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 18:53:14 -05:00
Owner
Copy Link

Originally created by @filipwiech on GitHub (May 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10630

Very recently llama.cpp project has merged the following PR:
https://github.com/ggml-org/llama.cpp/pull/13388
It seems to significantly increase the prompt processing speed on Apple Silicon (Metal backend) for Mixture-of-Experts models, such as Qwen 3 30B-A3B. Would be great to have it integrated into the next Ollama version if possible. 👍

CC @jmorganca. 😉

Originally created by @filipwiech on GitHub (May 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10630 Very recently llama.cpp project has merged the following PR: https://github.com/ggml-org/llama.cpp/pull/13388 It seems to significantly increase the prompt processing speed on Apple Silicon (Metal backend) for Mixture-of-Experts models, such as Qwen 3 30B-A3B. Would be great to have it integrated into the next Ollama version if possible. 👍 CC @jmorganca. 😉
GiteaMirror added the feature request label 2026-04-12 18:53:14 -05:00
GiteaMirror commented 2026-04-12 18:53:16 -05:00
Author
Owner
Copy Link

@filipwiech commented on GitHub (May 13, 2025):

This should be now taken care of by the PR #10655, thanks @jmorganca! 🙂

<!-- gh-comment-id:2876213450 --> @filipwiech commented on GitHub (May 13, 2025): This should be now taken care of by the PR #10655, thanks @jmorganca! 🙂
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 feature 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#6993
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?