github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #14051] [MERGED] model: add qwen3-next architecture #40359

New Issue
Closed
opened 2026-04-23 01:16:19 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-23 01:16:19 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/14051
Author: @jmorganca
Created: 2/3/2026
Status: ✅ Merged
Merged: 2/4/2026
Merged by: @jmorganca

Base: main ← Head: ollama-qwen3-next

📝 Commits (10+)

📊 Changes

29 files changed (+3614 additions, -12 deletions)

View changed files

📝 convert/convert.go (+2 -0)
➕ convert/convert_qwen3next.go (+512 -0)
📝 convert/reader.go (+1 -0)
📝 convert/reader_safetensors.go (+1 -0)
📝 fs/ggml/ggml.go (+2 -0)
📝 kvcache/cache.go (+7 -0)
➕ llama/patches/0033-ggml-metal-solve_tri.patch (+276 -0)
📝 ml/backend.go (+26 -0)
📝 ml/backend/ggml/ggml.go (+71 -1)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.cpp (+20 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.h (+1 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.m (+11 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal (+81 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-impl.h (+21 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-ops.cpp (+63 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-ops.h (+1 -0)
📝 ml/backend/ggml/ggml/src/ggml-metal/ggml-metal.metal (+60 -0)
📝 model/model_test.go (+12 -0)
📝 model/models/models.go (+1 -0)
➕ model/models/qwen3next/attention.go (+103 -0)

...and 9 more files

📄 Description

No description provided

🔄 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/14051 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 2/3/2026 **Status:** ✅ Merged **Merged:** 2/4/2026 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `ollama-qwen3-next` --- ### 📝 Commits (10+) - [`ed87d8a`](https://github.com/ollama/ollama/commit/ed87d8aab98f1547fdb5761c72bb5b3c1ae35f1d) model: add qwen3-next architecture - [`708d05c`](https://github.com/ollama/ollama/commit/708d05ce21d6f8f223958cdcf4516f96954cf761) wip - [`ce95c2e`](https://github.com/ollama/ollama/commit/ce95c2ea9e4b480bd3e2b21f3a4f36ca4c58e668) wip - [`b42e9a4`](https://github.com/ollama/ollama/commit/b42e9a42ce7d3ce95b08844a9f0c2fe9577afbc7) clamp - [`e983814`](https://github.com/ollama/ollama/commit/e98381435060b45980cb98a782d6f1415c37d4ad) prune kv cache after checkpoint - [`dc6452b`](https://github.com/ollama/ollama/commit/dc6452bfed0dae99a13cf8b2d7d8936b1b1954d3) add more cache states - [`6afc6d5`](https://github.com/ollama/ollama/commit/6afc6d5fe5de6f51f5cb0ea2f54a9f5c9db277d3) better safety around the cache - [`7b308a0`](https://github.com/ollama/ollama/commit/7b308a0063e531bd8af2fc59c0b8aedba07c22a2) fix solve_tri patch for rebased base - [`2b2b8cf`](https://github.com/ollama/ollama/commit/2b2b8cf42ef2dff117feb10e60895f2a93befb3e) fix qwen3next tests crashing on empty compute graphs - [`9a67cf6`](https://github.com/ollama/ollama/commit/9a67cf6b68bcb441d70789cf0b7d57ff85e6866c) fix qwen3next linter errors ### 📊 Changes **29 files changed** (+3614 additions, -12 deletions) <details> <summary>View changed files</summary> 📝 `convert/convert.go` (+2 -0) ➕ `convert/convert_qwen3next.go` (+512 -0) 📝 `convert/reader.go` (+1 -0) 📝 `convert/reader_safetensors.go` (+1 -0) 📝 `fs/ggml/ggml.go` (+2 -0) 📝 `kvcache/cache.go` (+7 -0) ➕ `llama/patches/0033-ggml-metal-solve_tri.patch` (+276 -0) 📝 `ml/backend.go` (+26 -0) 📝 `ml/backend/ggml/ggml.go` (+71 -1) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.cpp` (+20 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.h` (+1 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-device.m` (+11 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.metal` (+81 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-impl.h` (+21 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-ops.cpp` (+63 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-ops.h` (+1 -0) 📝 `ml/backend/ggml/ggml/src/ggml-metal/ggml-metal.metal` (+60 -0) 📝 `model/model_test.go` (+12 -0) 📝 `model/models/models.go` (+1 -0) ➕ `model/models/qwen3next/attention.go` (+103 -0) _...and 9 more files_ </details> ### 📄 Description _No description provided_ --- <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 2026-04-23 01:16:20 -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#40359
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?