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 #14913] [MERGED] mlx: add op wrappers for Conv2d, Pad, activations, trig, and masked SDPA #46160

New Issue
Closed
opened 2026-04-25 01:41:00 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 01:41:00 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/14913
Author: @dhiltgen
Created: 3/17/2026
Status: ✅ Merged
Merged: 4/13/2026
Merged by: @dhiltgen

Base: main ← Head: mlx-new-ops

📝 Commits (3)

  • dc72de8 mlx: add op wrappers for Conv2d, Pad, activations, trig, and masked SDPA
  • 186ab84 review comments
  • 72fe790 mlx: fix ScaledDotProductAttentionMasked to consult the mask argument

📊 Changes

3 files changed (+216 additions, -39 deletions)

View changed files

📝 x/create/client/quantize.go (+1 -1)
📝 x/mlxrunner/mlx/act.go (+51 -10)
📝 x/mlxrunner/mlx/ops_extra.go (+164 -28)

📄 Description

Add Conv2d, flexible Pad (with axes/mode), PadConstant, Maximum, Minimum, Softplus, ReLU, GLU, Clamp, Sin, Cos, Clip, ScaledDotProductAttentionMasked, and RoPEWithFreqs. Refactor RoPEWithBase to delegate to RoPEWithFreqs.

🔄 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/14913 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 3/17/2026 **Status:** ✅ Merged **Merged:** 4/13/2026 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `mlx-new-ops` --- ### 📝 Commits (3) - [`dc72de8`](https://github.com/ollama/ollama/commit/dc72de82913b8eb7bc9e92de6adf0a190a119c83) mlx: add op wrappers for Conv2d, Pad, activations, trig, and masked SDPA - [`186ab84`](https://github.com/ollama/ollama/commit/186ab849eb966e958686db86438470bf3028afad) review comments - [`72fe790`](https://github.com/ollama/ollama/commit/72fe79007a3ea83b237f3ab25676764c580c18b8) mlx: fix ScaledDotProductAttentionMasked to consult the mask argument ### 📊 Changes **3 files changed** (+216 additions, -39 deletions) <details> <summary>View changed files</summary> 📝 `x/create/client/quantize.go` (+1 -1) 📝 `x/mlxrunner/mlx/act.go` (+51 -10) 📝 `x/mlxrunner/mlx/ops_extra.go` (+164 -28) </details> ### 📄 Description Add Conv2d, flexible Pad (with axes/mode), PadConstant, Maximum, Minimum, Softplus, ReLU, GLU, Clamp, Sin, Cos, Clip, ScaledDotProductAttentionMasked, and RoPEWithFreqs. Refactor RoPEWithBase to delegate to RoPEWithFreqs. --- <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 2026-04-25 01:41:00 -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#46160
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?