[PR #3086] [MERGED] Import server.cpp to retain llava support #21600

Closed
opened 2026-04-19 15:44:24 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/3086
Author: @dhiltgen
Created: 3/12/2024
Status: Merged
Merged: 3/15/2024
Merged by: @dhiltgen

Base: mainHead: import_server


📝 Commits (2)

  • 9ac6440 Import server.cpp as of b2356
  • 85129d3 Adapt our build for imported server.cpp

📊 Changes

12 files changed (+43307 additions, -23 deletions)

View changed files

📝 llm/ext_server/CMakeLists.txt (+2 -6)
llm/ext_server/completion.js.hpp (+485 -0)
llm/ext_server/httplib.h (+8794 -0)
llm/ext_server/index.html.hpp (+2791 -0)
llm/ext_server/index.js.hpp (+1903 -0)
llm/ext_server/json-schema-to-grammar.mjs.hpp (+311 -0)
llm/ext_server/json.hpp (+24596 -0)
llm/ext_server/oai.hpp (+225 -0)
llm/ext_server/server.cpp (+3558 -0)
llm/ext_server/utils.hpp (+633 -0)
📝 llm/generate/gen_common.sh (+5 -8)
📝 llm/generate/gen_windows.ps1 (+4 -9)

📄 Description

Recent refactoring upstream has temporarily(?) removed llava support from the server.cpp code, which we rely on. This pulls the server just before that change into our repo so we can keep current with the base llama.cpp code updates until llava support is added back.

Verified on Mac, Linux 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/3086 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 3/12/2024 **Status:** ✅ Merged **Merged:** 3/15/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `import_server` --- ### 📝 Commits (2) - [`9ac6440`](https://github.com/ollama/ollama/commit/9ac6440da37832861410d7e8611b5a320e58901c) Import server.cpp as of b2356 - [`85129d3`](https://github.com/ollama/ollama/commit/85129d3a32ffadd8ba34d8221cf54e3f74e73eee) Adapt our build for imported server.cpp ### 📊 Changes **12 files changed** (+43307 additions, -23 deletions) <details> <summary>View changed files</summary> 📝 `llm/ext_server/CMakeLists.txt` (+2 -6) ➕ `llm/ext_server/completion.js.hpp` (+485 -0) ➕ `llm/ext_server/httplib.h` (+8794 -0) ➕ `llm/ext_server/index.html.hpp` (+2791 -0) ➕ `llm/ext_server/index.js.hpp` (+1903 -0) ➕ `llm/ext_server/json-schema-to-grammar.mjs.hpp` (+311 -0) ➕ `llm/ext_server/json.hpp` (+24596 -0) ➕ `llm/ext_server/oai.hpp` (+225 -0) ➕ `llm/ext_server/server.cpp` (+3558 -0) ➕ `llm/ext_server/utils.hpp` (+633 -0) 📝 `llm/generate/gen_common.sh` (+5 -8) 📝 `llm/generate/gen_windows.ps1` (+4 -9) </details> ### 📄 Description Recent refactoring upstream has temporarily(?) removed llava support from the server.cpp code, which we rely on. This pulls the server just before that change into our repo so we can keep current with the base llama.cpp code updates until llava support is added back. Verified on Mac, Linux 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 2026-04-19 15:44:24 -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#21600