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 #11823] [MERGED] update vendored llama.cpp and ggml #60325

New Issue
Closed
opened 2026-04-29 15:15:07 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 15:15:07 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11823
Author: @mxyng
Created: 8/9/2025
Status: ✅ Merged
Merged: 8/14/2025
Merged by: @mxyng

Base: main ← Head: gpt-oss-bump

📝 Commits (10+)

  • 7b45a55 TEMPORARY: Update the llama.cpp upstream to my fork's Granite Four branch
  • 68a22ac feat: Update all patches
  • d206bc8 feat: Sync llama.cpp and ggml
  • 2d6aaf9 fix: Update rsync-filter for all moved/new/removed files
  • 740a1ae fix: Add files missing from sync
  • 22d2205 fix: Update ggml rsync-filter for new ggml-cpu/arch subdirs
  • 59d7586 fix: Add ggml files missing from sync
  • 1e02876 fix: Narrow llama.cpp rsync-filter to not include mtmd main tool cpp files
  • a0249d4 fix: Remove mtmd main cpp files
  • 64d4dca fix: Add missing include in sampling_ext.cpp

📊 Changes

243 files changed (+156798 additions, -48333 deletions)

View changed files

📝 CMakeLists.txt (+2 -1)
📝 Makefile.sync (+17 -8)
📝 convert/reader.go (+1 -0)
📝 fs/ggml/ggml.go (+4 -9)
📝 llama/build-info.cpp (+1 -1)
📝 llama/llama.cpp/.rsync-filter (+32 -23)
📝 llama/llama.cpp/common/common.cpp (+102 -119)
📝 llama/llama.cpp/common/common.go (+2 -2)
📝 llama/llama.cpp/common/common.h (+55 -24)
📝 llama/llama.cpp/common/json-schema-to-grammar.cpp (+5 -47)
📝 llama/llama.cpp/common/json-schema-to-grammar.h (+4 -4)
📝 llama/llama.cpp/common/sampling.cpp (+7 -8)
📝 llama/llama.cpp/include/llama.h (+183 -202)
📝 llama/llama.cpp/src/llama-arch.cpp (+596 -3)
📝 llama/llama.cpp/src/llama-arch.h (+62 -1)
📝 llama/llama.cpp/src/llama-batch.cpp (+774 -271)
📝 llama/llama.cpp/src/llama-batch.h (+126 -55)
📝 llama/llama.cpp/src/llama-chat.cpp (+120 -11)
📝 llama/llama.cpp/src/llama-chat.h (+6 -0)
📝 llama/llama.cpp/src/llama-context.cpp (+681 -467)

...and 80 more files

📄 Description

This change updates llama.cpp to e54d41befc and updates Ollama's gpt-oss implementation to be much faster thanks to the amazing work done by ggml-org

Special thanks to @gabe-l-hart for all his hard work with the initial bump

🔄 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/11823 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 8/9/2025 **Status:** ✅ Merged **Merged:** 8/14/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `gpt-oss-bump` --- ### 📝 Commits (10+) - [`7b45a55`](https://github.com/ollama/ollama/commit/7b45a5520e0dd2baaf5725f878f83daaee51f04b) TEMPORARY: Update the llama.cpp upstream to my fork's Granite Four branch - [`68a22ac`](https://github.com/ollama/ollama/commit/68a22ac1eda922568d0069788efcc91bc0f677bc) feat: Update all patches - [`d206bc8`](https://github.com/ollama/ollama/commit/d206bc8c8645a0f8fd587dacd12cdf14f6c2291c) feat: Sync llama.cpp and ggml - [`2d6aaf9`](https://github.com/ollama/ollama/commit/2d6aaf958fa6be9c1ff0dec5649347196a21ec0f) fix: Update rsync-filter for all moved/new/removed files - [`740a1ae`](https://github.com/ollama/ollama/commit/740a1aef00c23ff9f254b5906a6e96745dd3c797) fix: Add files missing from sync - [`22d2205`](https://github.com/ollama/ollama/commit/22d2205616fa2c31d7d4ac74efa4beab006fd888) fix: Update ggml rsync-filter for new ggml-cpu/arch subdirs - [`59d7586`](https://github.com/ollama/ollama/commit/59d7586765fb2d4f7661bd5e639b182cabb8f6ef) fix: Add ggml files missing from sync - [`1e02876`](https://github.com/ollama/ollama/commit/1e02876646436eda9d6e2a749aa632104e637ec1) fix: Narrow llama.cpp rsync-filter to not include mtmd main tool cpp files - [`a0249d4`](https://github.com/ollama/ollama/commit/a0249d4fff84b49ffe22b593a79bc6a10e4c7506) fix: Remove mtmd main cpp files - [`64d4dca`](https://github.com/ollama/ollama/commit/64d4dcaf0215d2c81ffc719066c2802ff7caeaeb) fix: Add missing include in sampling_ext.cpp ### 📊 Changes **243 files changed** (+156798 additions, -48333 deletions) <details> <summary>View changed files</summary> 📝 `CMakeLists.txt` (+2 -1) 📝 `Makefile.sync` (+17 -8) 📝 `convert/reader.go` (+1 -0) 📝 `fs/ggml/ggml.go` (+4 -9) 📝 `llama/build-info.cpp` (+1 -1) 📝 `llama/llama.cpp/.rsync-filter` (+32 -23) 📝 `llama/llama.cpp/common/common.cpp` (+102 -119) 📝 `llama/llama.cpp/common/common.go` (+2 -2) 📝 `llama/llama.cpp/common/common.h` (+55 -24) 📝 `llama/llama.cpp/common/json-schema-to-grammar.cpp` (+5 -47) 📝 `llama/llama.cpp/common/json-schema-to-grammar.h` (+4 -4) 📝 `llama/llama.cpp/common/sampling.cpp` (+7 -8) 📝 `llama/llama.cpp/include/llama.h` (+183 -202) 📝 `llama/llama.cpp/src/llama-arch.cpp` (+596 -3) 📝 `llama/llama.cpp/src/llama-arch.h` (+62 -1) 📝 `llama/llama.cpp/src/llama-batch.cpp` (+774 -271) 📝 `llama/llama.cpp/src/llama-batch.h` (+126 -55) 📝 `llama/llama.cpp/src/llama-chat.cpp` (+120 -11) 📝 `llama/llama.cpp/src/llama-chat.h` (+6 -0) 📝 `llama/llama.cpp/src/llama-context.cpp` (+681 -467) _...and 80 more files_ </details> ### 📄 Description This change updates llama.cpp to https://github.com/ggml-org/llama.cpp/commit/e54d41befcc1575f4c898c5ff4ef43970cead75f and updates Ollama's gpt-oss implementation to be much faster thanks to the amazing work done by [ggml-org](https://github.com/ggml-org) Special thanks to @gabe-l-hart for all his hard work with the initial bump --- <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 15:15:07 -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#60325
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?