[PR #7434] [MERGED] Remove server.cpp compatibility code #22961

Closed
opened 2026-04-19 16:41:12 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7434
Author: @jessegross
Created: 10/31/2024
Status: Merged
Merged: 11/6/2024
Merged by: @jessegross

Base: mainHead: jessegross/runner_cleanup


📝 Commits (2)

  • 2606a40 sched: Lift parallel restriction for multimodal models except mllama
  • 83ae84a runner.go: Remove unused arguments

📊 Changes

6 files changed (+4 additions, -18 deletions)

View changed files

📝 api/types.go (+1 -2)
📝 docs/api.md (+0 -1)
📝 llama/runner/runner.go (+0 -6)
📝 llm/server.go (+0 -5)
📝 parser/parser_test.go (+0 -1)
📝 server/sched.go (+3 -3)

📄 Description

Some interfaces in the Go runner were kept the same as server.cpp for compatibility, we can now start to make things more natural.

The one user-facing impact of this change is that multimodal models other than mllama can now support parallel requests.


🔄 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/7434 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 10/31/2024 **Status:** ✅ Merged **Merged:** 11/6/2024 **Merged by:** [@jessegross](https://github.com/jessegross) **Base:** `main` ← **Head:** `jessegross/runner_cleanup` --- ### 📝 Commits (2) - [`2606a40`](https://github.com/ollama/ollama/commit/2606a40f13854a93e11d384027c0407dcc7eb85c) sched: Lift parallel restriction for multimodal models except mllama - [`83ae84a`](https://github.com/ollama/ollama/commit/83ae84a7cb91d2dbf055435995d74511718cbdf5) runner.go: Remove unused arguments ### 📊 Changes **6 files changed** (+4 additions, -18 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+1 -2) 📝 `docs/api.md` (+0 -1) 📝 `llama/runner/runner.go` (+0 -6) 📝 `llm/server.go` (+0 -5) 📝 `parser/parser_test.go` (+0 -1) 📝 `server/sched.go` (+3 -3) </details> ### 📄 Description Some interfaces in the Go runner were kept the same as server.cpp for compatibility, we can now start to make things more natural. The one user-facing impact of this change is that multimodal models other than mllama can now support parallel requests. --- <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 16:41:12 -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#22961