[PR #6123] [MERGED] llama: Runtime selection of new or old runners #17297

Closed
opened 2026-04-16 05:58:29 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/6123
Author: @dhiltgen
Created: 8/1/2024
Status: Merged
Merged: 8/1/2024
Merged by: @dhiltgen

Base: jmorganca/llamaHead: go_server_unified


📝 Commits (4)

  • c1384c8 Implement timings response in Go server
  • 46c5f5f Runtime selection of new or old runners
  • 343aba9 harden integration tests
  • 3cc7ec4 fix dolphin-mistral

📊 Changes

8 files changed (+481 additions, -176 deletions)

View changed files

📝 envconfig/config.go (+12 -2)
📝 integration/concurrency_test.go (+1 -1)
📝 integration/utils_test.go (+1 -1)
📝 llama/Makefile (+252 -63)
📝 llama/runner/runner.go (+124 -20)
📝 llm/generate/gen_darwin.sh (+1 -1)
📝 llm/llm.go (+66 -0)
📝 llm/server.go (+24 -88)

📄 Description

This change pulls out the ~minimal set of changes from #5287 to be able to build locally and run either the C++ or Go runner

Carries #6122

This wont be ready to merge to main until other build rigging changes from the other PR are factored in.


🔄 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/6123 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 8/1/2024 **Status:** ✅ Merged **Merged:** 8/1/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `jmorganca/llama` ← **Head:** `go_server_unified` --- ### 📝 Commits (4) - [`c1384c8`](https://github.com/ollama/ollama/commit/c1384c8bcc21b8905214e621c1bda765de724489) Implement timings response in Go server - [`46c5f5f`](https://github.com/ollama/ollama/commit/46c5f5fd9e5b03c8f784aad8ee2e6377967c12c6) Runtime selection of new or old runners - [`343aba9`](https://github.com/ollama/ollama/commit/343aba9fcaef4c4cdab54d6eecc68742246f27f9) harden integration tests - [`3cc7ec4`](https://github.com/ollama/ollama/commit/3cc7ec4429da3b9e22cc1fcf8c149777f2b423f7) fix dolphin-mistral ### 📊 Changes **8 files changed** (+481 additions, -176 deletions) <details> <summary>View changed files</summary> 📝 `envconfig/config.go` (+12 -2) 📝 `integration/concurrency_test.go` (+1 -1) 📝 `integration/utils_test.go` (+1 -1) 📝 `llama/Makefile` (+252 -63) 📝 `llama/runner/runner.go` (+124 -20) 📝 `llm/generate/gen_darwin.sh` (+1 -1) 📝 `llm/llm.go` (+66 -0) 📝 `llm/server.go` (+24 -88) </details> ### 📄 Description This change pulls out the ~minimal set of changes from #5287 to be able to build locally and run either the C++ or Go runner Carries #6122 This wont be ready to merge to main until other build rigging changes from the other PR are factored in. --- <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 2026-04-16 05:58:29 -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#17297