github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #11204] [MERGED] add new gemma model #60174

New Issue
Closed
opened 2026-04-29 15:05:33 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 15:05:33 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11204
Author: @mxyng
Created: 6/26/2025
Status: ✅ Merged
Merged: 6/26/2025
Merged by: @mxyng

Base: main ← Head: mxyng/gemma

📝 Commits (4)

📊 Changes

25 files changed (+6084 additions, -54 deletions)

View changed files

📝 convert/convert.go (+2 -0)
➕ convert/convert_gemma3n.go (+168 -0)
📝 fs/config.go (+1 -0)
📝 fs/ggml/ggml.go (+5 -0)
📝 fs/ggml/gguf.go (+4 -0)
📝 go.mod (+1 -1)
📝 llama/patches/0005-solar-pro.patch (+1 -1)
📝 llama/patches/0008-ensure-KV-cache-is-fully-defragmented.patch (+3 -3)
📝 llama/patches/0015-add-argsort-and-cuda-copy-for-i32.patch (+6 -6)
➕ llama/patches/0019-metal-add-mean-kernel-14267.patch (+169 -0)
➕ llama/patches/0020-CUDA-add-mean-operation-14313.patch (+5089 -0)
📝 ml/backend.go (+8 -0)
📝 ml/backend/ggml/ggml.go (+56 -1)
📝 ml/backend/ggml/ggml/src/ggml-cuda/common.cuh (+20 -0)
📝 ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu (+5 -0)
➕ ml/backend/ggml/ggml/src/ggml-cuda/mean.cu (+19 -0)
➕ ml/backend/ggml/ggml/src/ggml-cuda/mean.cuh (+3 -0)
📝 ml/backend/ggml/ggml/src/ggml-cuda/sumrows.cu (+5 -18)
📝 ml/backend/ggml/ggml/src/ggml-cuda/sumrows.cuh (+0 -1)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal (+39 -9)

...and 5 more files

📄 Description

text only (for now)

credit to llama.cpp for mean kernels for metal and cuda

🔄 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/11204 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 6/26/2025 **Status:** ✅ Merged **Merged:** 6/26/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/gemma` --- ### 📝 Commits (4) - [`23daa76`](https://github.com/ollama/ollama/commit/23daa76141b99157088f86a3fb600e2c71de1af7) update patches - [`ec0d810`](https://github.com/ollama/ollama/commit/ec0d810054647637781409b698bc8e5baf5b37e1) cherry pick metal mean kernel - [`19f6b91`](https://github.com/ollama/ollama/commit/19f6b91cf3b832cae94b74e7cce21e105b19f317) cherry pick cuda mean kernel - [`32c946d`](https://github.com/ollama/ollama/commit/32c946da03c82d02b052294f2dd9514774107391) gemma3n ### 📊 Changes **25 files changed** (+6084 additions, -54 deletions) <details> <summary>View changed files</summary> 📝 `convert/convert.go` (+2 -0) ➕ `convert/convert_gemma3n.go` (+168 -0) 📝 `fs/config.go` (+1 -0) 📝 `fs/ggml/ggml.go` (+5 -0) 📝 `fs/ggml/gguf.go` (+4 -0) 📝 `go.mod` (+1 -1) 📝 `llama/patches/0005-solar-pro.patch` (+1 -1) 📝 `llama/patches/0008-ensure-KV-cache-is-fully-defragmented.patch` (+3 -3) 📝 `llama/patches/0015-add-argsort-and-cuda-copy-for-i32.patch` (+6 -6) ➕ `llama/patches/0019-metal-add-mean-kernel-14267.patch` (+169 -0) ➕ `llama/patches/0020-CUDA-add-mean-operation-14313.patch` (+5089 -0) 📝 `ml/backend.go` (+8 -0) 📝 `ml/backend/ggml/ggml.go` (+56 -1) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/common.cuh` (+20 -0) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu` (+5 -0) ➕ `ml/backend/ggml/ggml/src/ggml-cuda/mean.cu` (+19 -0) ➕ `ml/backend/ggml/ggml/src/ggml-cuda/mean.cuh` (+3 -0) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/sumrows.cu` (+5 -18) 📝 `ml/backend/ggml/ggml/src/ggml-cuda/sumrows.cuh` (+0 -1) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal` (+39 -9) _...and 5 more files_ </details> ### 📄 Description text only (for now) credit to llama.cpp for mean kernels for metal and cuda --- <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 15:05:33 -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#60174
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?