[PR #10192] [MERGED] llama: update to commit 7538246e #13174

Closed
opened 2026-04-13 00:19:46 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10192
Author: @jmorganca
Created: 4/9/2025
Status: Merged
Merged: 4/16/2025
Merged by: @jmorganca

Base: mainHead: jmorganca/llama-update-2


📝 Commits (1)

  • 0602f31 llama: update to commit 71e90e88

📊 Changes

160 files changed (+42991 additions, -33852 deletions)

View changed files

📝 .github/workflows/test.yaml (+2 -2)
📝 CMakeLists.txt (+1 -1)
📝 Makefile.sync (+5 -5)
📝 llama/build-info.cpp (+1 -1)
📝 llama/llama.cpp/.rsync-filter (+1 -0)
📝 llama/llama.cpp/common/common.cpp (+42 -503)
📝 llama/llama.cpp/common/common.h (+35 -40)
📝 llama/llama.cpp/common/json-schema-to-grammar.cpp (+4 -5)
📝 llama/llama.cpp/common/json-schema-to-grammar.h (+0 -1)
📝 llama/llama.cpp/common/sampling.cpp (+48 -7)
llama/llama.cpp/examples/llava/clip-impl.h (+344 -0)
📝 llama/llama.cpp/examples/llava/clip.cpp (+961 -1072)
📝 llama/llama.cpp/examples/llava/clip.h (+34 -16)
📝 llama/llama.cpp/examples/llava/llava.cpp (+57 -46)
📝 llama/llama.cpp/include/llama.h (+131 -38)
📝 llama/llama.cpp/src/llama-adapter.cpp (+55 -20)
📝 llama/llama.cpp/src/llama-adapter.h (+11 -9)
📝 llama/llama.cpp/src/llama-arch.cpp (+241 -18)
📝 llama/llama.cpp/src/llama-arch.h (+28 -0)
📝 llama/llama.cpp/src/llama-batch.h (+2 -2)

...and 80 more files

📄 Description

Important to test:

  • Cache defrag on the llama runner
  • Vision models
  • Loading model data from paths with unicode on Linux, macOS and Windows

🔄 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/10192 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 4/9/2025 **Status:** ✅ Merged **Merged:** 4/16/2025 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `jmorganca/llama-update-2` --- ### 📝 Commits (1) - [`0602f31`](https://github.com/ollama/ollama/commit/0602f31c3fce1010d87170793c4281656e793a20) llama: update to commit 71e90e88 ### 📊 Changes **160 files changed** (+42991 additions, -33852 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/test.yaml` (+2 -2) 📝 `CMakeLists.txt` (+1 -1) 📝 `Makefile.sync` (+5 -5) 📝 `llama/build-info.cpp` (+1 -1) 📝 `llama/llama.cpp/.rsync-filter` (+1 -0) 📝 `llama/llama.cpp/common/common.cpp` (+42 -503) 📝 `llama/llama.cpp/common/common.h` (+35 -40) 📝 `llama/llama.cpp/common/json-schema-to-grammar.cpp` (+4 -5) 📝 `llama/llama.cpp/common/json-schema-to-grammar.h` (+0 -1) 📝 `llama/llama.cpp/common/sampling.cpp` (+48 -7) ➕ `llama/llama.cpp/examples/llava/clip-impl.h` (+344 -0) 📝 `llama/llama.cpp/examples/llava/clip.cpp` (+961 -1072) 📝 `llama/llama.cpp/examples/llava/clip.h` (+34 -16) 📝 `llama/llama.cpp/examples/llava/llava.cpp` (+57 -46) 📝 `llama/llama.cpp/include/llama.h` (+131 -38) 📝 `llama/llama.cpp/src/llama-adapter.cpp` (+55 -20) 📝 `llama/llama.cpp/src/llama-adapter.h` (+11 -9) 📝 `llama/llama.cpp/src/llama-arch.cpp` (+241 -18) 📝 `llama/llama.cpp/src/llama-arch.h` (+28 -0) 📝 `llama/llama.cpp/src/llama-batch.h` (+2 -2) _...and 80 more files_ </details> ### 📄 Description Important to test: - [x] Cache defrag on the llama runner - [x] Vision models - [x] Loading model data from paths with unicode on Linux, macOS and Windows --- <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 00:19:46 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13174