github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #13451] [MERGED] GGML update to ec98e2002 #14214

New Issue
Closed
opened 2026-04-13 00:48:33 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:48:33 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13451
Author: @dhiltgen
Created: 12/12/2025
Status: ✅ Merged
Merged: 12/17/2025
Merged by: @dhiltgen

Base: main ← Head: ggml_bump

📝 Commits (5)

📊 Changes

127 files changed (+8158 additions, -6740 deletions)

View changed files

📝 Makefile.sync (+1 -1)
📝 kvcache/causal.go (+2 -15)
📝 llama/build-info.cpp (+1 -1)
📝 llama/llama.cpp/.rsync-filter (+3 -0)
📝 llama/llama.cpp/common/common.cpp (+130 -67)
📝 llama/llama.cpp/common/common.h (+40 -16)
📝 llama/llama.cpp/common/json-schema-to-grammar.cpp (+132 -3)
📝 llama/llama.cpp/common/json-schema-to-grammar.h (+20 -0)
📝 llama/llama.cpp/common/log.cpp (+5 -0)
📝 llama/llama.cpp/common/log.h (+1 -0)
📝 llama/llama.cpp/common/sampling.cpp (+91 -92)
📝 llama/llama.cpp/common/sampling.h (+11 -6)
📝 llama/llama.cpp/include/llama.h (+18 -1)
📝 llama/llama.cpp/src/llama-arch.cpp (+1905 -2299)
📝 llama/llama.cpp/src/llama-arch.h (+8 -2)
📝 llama/llama.cpp/src/llama-batch.cpp (+12 -2)
📝 llama/llama.cpp/src/llama-batch.h (+4 -2)
📝 llama/llama.cpp/src/llama-context.cpp (+93 -23)
📝 llama/llama.cpp/src/llama-context.h (+8 -2)
📝 llama/llama.cpp/src/llama-graph.cpp (+76 -18)

...and 80 more files

📄 Description

Adjustments required for this update:

  • Remove MaskBatchPadding as GGML_KQ_MASK_PAD is no longer present (no padding required)
  • Solar Pro refactoring
  • Graph memory reporting
  • Removed temporary carry of nemotron 3 nano commits as a patch (they're included in this update)

🔄 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/13451 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 12/12/2025 **Status:** ✅ Merged **Merged:** 12/17/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `ggml_bump` --- ### 📝 Commits (5) - [`f4d9e2f`](https://github.com/ollama/ollama/commit/f4d9e2f935f0bb74f3ca4e604b6bdaf2434f57bc) Revert "add support for NVIDIA Nemotron 3 Nano" - [`79c7f54`](https://github.com/ollama/ollama/commit/79c7f54881f8169b327e527e3bfce84e28f16b2d) GGML update to 380b4c984 - [`d207c02`](https://github.com/ollama/ollama/commit/d207c02d118b1a9d69a118f72e216c95d9848738) update to c45f89d55 - [`6a43120`](https://github.com/ollama/ollama/commit/6a4312075457d6cf3fa8830e69c3d4488eb88205) ec98e2002 - [`d7cda4f`](https://github.com/ollama/ollama/commit/d7cda4f5ac76a0dc85ec14fc4de8158ab5c87b5d) review comments ### 📊 Changes **127 files changed** (+8158 additions, -6740 deletions) <details> <summary>View changed files</summary> 📝 `Makefile.sync` (+1 -1) 📝 `kvcache/causal.go` (+2 -15) 📝 `llama/build-info.cpp` (+1 -1) 📝 `llama/llama.cpp/.rsync-filter` (+3 -0) 📝 `llama/llama.cpp/common/common.cpp` (+130 -67) 📝 `llama/llama.cpp/common/common.h` (+40 -16) 📝 `llama/llama.cpp/common/json-schema-to-grammar.cpp` (+132 -3) 📝 `llama/llama.cpp/common/json-schema-to-grammar.h` (+20 -0) 📝 `llama/llama.cpp/common/log.cpp` (+5 -0) 📝 `llama/llama.cpp/common/log.h` (+1 -0) 📝 `llama/llama.cpp/common/sampling.cpp` (+91 -92) 📝 `llama/llama.cpp/common/sampling.h` (+11 -6) 📝 `llama/llama.cpp/include/llama.h` (+18 -1) 📝 `llama/llama.cpp/src/llama-arch.cpp` (+1905 -2299) 📝 `llama/llama.cpp/src/llama-arch.h` (+8 -2) 📝 `llama/llama.cpp/src/llama-batch.cpp` (+12 -2) 📝 `llama/llama.cpp/src/llama-batch.h` (+4 -2) 📝 `llama/llama.cpp/src/llama-context.cpp` (+93 -23) 📝 `llama/llama.cpp/src/llama-context.h` (+8 -2) 📝 `llama/llama.cpp/src/llama-graph.cpp` (+76 -18) _...and 80 more files_ </details> ### 📄 Description Adjustments required for this update: - Remove MaskBatchPadding as GGML_KQ_MASK_PAD is no longer present (no padding required) - Solar Pro refactoring - Graph memory reporting - Removed temporary carry of nemotron 3 nano commits as a patch (they're included in this update) --- <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 2026-04-13 00:48:33 -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#14214
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?