github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #2143] [MERGED] Refine debug logging for llm #10797

New Issue
Closed
opened 2026-04-12 23:11:08 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:11:08 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/2143
Author: @dhiltgen
Created: 1/22/2024
Status: ✅ Merged
Merged: 1/22/2024
Merged by: @dhiltgen

Base: main ← Head: llm_verbosity

📝 Commits (1)

  • 730dcfc Refine debug logging for llm

📊 Changes

3 files changed (+13 additions, -5 deletions)

View changed files

📝 llm/dyn_ext_server.go (+6 -0)
📝 llm/ext_server/ext_server.cpp (+6 -5)
📝 llm/ext_server/ext_server.h (+1 -0)

📄 Description

This wires up logging in llama.cpp to always go to stderr, and also turns up logging if OLLAMA_DEBUG is set.

This solves a couple problems. We used to emit one line to llama.log in verbose/debug mode before shifting to stdout. Now all the logging from llama.cpp will go to stderr, and the verbosity can be controlled at runtime.

🔄 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/2143 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/22/2024 **Status:** ✅ Merged **Merged:** 1/22/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `llm_verbosity` --- ### 📝 Commits (1) - [`730dcfc`](https://github.com/ollama/ollama/commit/730dcfcc7ab3c1fc24417887533eee8c72e45a1c) Refine debug logging for llm ### 📊 Changes **3 files changed** (+13 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `llm/dyn_ext_server.go` (+6 -0) 📝 `llm/ext_server/ext_server.cpp` (+6 -5) 📝 `llm/ext_server/ext_server.h` (+1 -0) </details> ### 📄 Description This wires up logging in llama.cpp to always go to stderr, and also turns up logging if OLLAMA_DEBUG is set. This solves a couple problems. We used to emit one line to llama.log in verbose/debug mode before shifting to stdout. Now all the logging from llama.cpp will go to stderr, and the verbosity can be controlled at runtime. --- <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 2026-04-12 23:11:08 -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#10797
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?