github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11834] Improve log readability by adding a single summary line after model load #7854

New Issue
Open
opened 2026-04-12 20:01:04 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 20:01:04 -05:00
Owner
Copy Link

Originally created by @kha84 on GitHub (Aug 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11834

Currently, Ollama’s logs make it hard to quickly see the key parameters with which a model was actually loaded. Important details — such as:

  • Model name
  • Context size
  • Whether flash attention was enabled
  • KV cache quantization setting
  • Device used (CPU/GPU, etc.)

— are scattered across multiple log lines, often printed by different parts of the runtime as the model initializes.

I understand this is partly due to the fact that model loading decisions happen dynamically in different modules, but it would greatly improve troubleshooting if Ollama printed one concise, standardized summary line once the model is fully loaded.

Example of what I have in mind:

Loaded model <MODEL_NAME> with context=<N>, flash_attention=<on/off>, kv_cache_quant=<mode>, device=<CPU/GPU/other>, ...

This would allow developers and users to:

  • Quickly confirm the model was loaded as intended
  • Spot mismatches in parameters without scanning multiple log entries
  • Troubleshoot tricky runtime behaviors more easily

Even if the underlying details are still logged separately during initialization, this one-line summary would be an excellent quality-of-life improvement.

Originally created by @kha84 on GitHub (Aug 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11834 Currently, Ollama’s logs make it hard to quickly see the key parameters with which a model was actually loaded. Important details — such as: * Model name * Context size * Whether flash attention was enabled * KV cache quantization setting * Device used (CPU/GPU, etc.) — are scattered across multiple log lines, often printed by different parts of the runtime as the model initializes. I understand this is partly due to the fact that model loading decisions happen dynamically in different modules, but it would greatly improve troubleshooting if Ollama printed **one concise, standardized summary line** once the model is fully loaded. Example of what I have in mind: ``` Loaded model <MODEL_NAME> with context=<N>, flash_attention=<on/off>, kv_cache_quant=<mode>, device=<CPU/GPU/other>, ... ``` This would allow developers and users to: * Quickly confirm the model was loaded as intended * Spot mismatches in parameters without scanning multiple log entries * Troubleshoot tricky runtime behaviors more easily Even if the underlying details are still logged separately during initialization, this one-line summary would be an excellent quality-of-life improvement.
GiteaMirror added the feature request label 2026-04-12 20:01:04 -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 feature 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#7854
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?