github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-14 11:01:34 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #12807] [MERGED] interleaved mrope #19232

New Issue
Closed
opened 2026-04-16 07:01:36 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 07:01:36 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12807
Author: @mxyng
Created: 10/28/2025
Status: ✅ Merged
Merged: 10/30/2025
Merged by: @mxyng

Base: main ← Head: mxyng/mrope-interleave

📝 Commits (2)

📊 Changes

10 files changed (+209 additions, -119 deletions)

View changed files

➕ llama/patches/0032-interleave-multi-rope.patch (+113 -0)
📝 ml/backend/ggml/ggml.go (+33 -19)
📝 ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp (+2 -5)
📝 ml/backend/ggml/ggml/src/ggml-cuda/rope.cu (+3 -9)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal (+3 -7)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal.metal (+3 -7)
📝 ml/backend/ggml/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp (+3 -9)
📝 ml/nn/rope/rope.go (+28 -14)
📝 model/models/qwen3vl/model.go (+8 -6)
📝 model/models/qwen3vl/model_text.go (+13 -43)

📄 Description

update mrope to work with qwen3vl's interleaved mrope

🔄 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/12807 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 10/28/2025 **Status:** ✅ Merged **Merged:** 10/30/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/mrope-interleave` --- ### 📝 Commits (2) - [`d84df6a`](https://github.com/ollama/ollama/commit/d84df6a4c555e6266fadab94da9266f6f7da9544) ml(ggml): mrope - [`d249ccc`](https://github.com/ollama/ollama/commit/d249ccc7f1321bf80a279e3693a70177d70b60da) interleave mrope ### 📊 Changes **10 files changed** (+209 additions, -119 deletions) <details> <summary>View changed files</summary> ➕ `llama/patches/0032-interleave-multi-rope.patch` (+113 -0) 📝 `ml/backend/ggml/ggml.go` (+33 -19) 📝 `ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp` (+2 -5) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/rope.cu` (+3 -9) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal` (+3 -7) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal.metal` (+3 -7) 📝 `ml/backend/ggml/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp` (+3 -9) 📝 `ml/nn/rope/rope.go` (+28 -14) 📝 `model/models/qwen3vl/model.go` (+8 -6) 📝 `model/models/qwen3vl/model_text.go` (+13 -43) </details> ### 📄 Description update mrope to work with [qwen3vl's interleaved mrope][1] [1]: https://github.com/huggingface/transformers/blob/4d0b6758b90aa54e4077171e6d42c55e0c01c622/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L349 --- <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 07:01:36 -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#19232
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?