github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #2163] [CLOSED] Expose llm library and layer info in verbose output #21344

New Issue
Closed
opened 2026-04-19 15:35:18 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 15:35:18 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/2163
Author: @dhiltgen
Created: 1/23/2024
Status: ❌ Closed

Base: main ← Head: llm_verbose_info

📝 Commits (1)

  • bebbc24 Expose llm library and layer info in verbose output

📊 Changes

5 files changed (+39 additions, -9 deletions)

View changed files

📝 api/types.go (+12 -0)
📝 llm/dyn_ext_server.go (+14 -5)
📝 llm/llama.go (+7 -0)
📝 llm/llm.go (+4 -4)
📝 server/routes.go (+2 -0)

📄 Description

This wires up additional information in our verbose metrics so you can see which llm library was used, and how many layers were loaded into the GPU.

Example output in the CLI:

./ollama run orca-mini
>>> /set verbose
Set 'verbose' mode.
>>> hello
 Hello, how can I assist you today?

total duration:       835.322625ms
load duration:        452.875µs
prompt eval count:    42 token(s)
prompt eval duration: 593.785ms
prompt eval rate:     70.73 tokens/s
eval count:           10 token(s)
eval duration:        240.374ms
eval rate:            41.60 tokens/s
llm library:          metal
GPU loaded layers:    1/27
>>>

The JSON payload:

{
  "model": "orca-mini",
  "created_at": "2024-01-23T20:23:02.168454Z",
  "response": " Hello, what can I assist you with today?",
  "done": true,
  "context": [
    31822,
    ...
  ],
  "total_duration": 849287875,
  "load_duration": 185542,
  "prompt_eval_count": 42,
  "prompt_eval_duration": 558791000,
  "eval_count": 11,
  "eval_duration": 290096000,
  "runtime": {
    "library": "metal",
    "layers": 1,
    "max_layers": 27
  }
}

🔄 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/2163 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/23/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `llm_verbose_info` --- ### 📝 Commits (1) - [`bebbc24`](https://github.com/ollama/ollama/commit/bebbc249f1ffe5a0c03f977cab39f4702763f808) Expose llm library and layer info in verbose output ### 📊 Changes **5 files changed** (+39 additions, -9 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+12 -0) 📝 `llm/dyn_ext_server.go` (+14 -5) 📝 `llm/llama.go` (+7 -0) 📝 `llm/llm.go` (+4 -4) 📝 `server/routes.go` (+2 -0) </details> ### 📄 Description This wires up additional information in our verbose metrics so you can see which llm library was used, and how many layers were loaded into the GPU. Example output in the CLI: ``` ./ollama run orca-mini >>> /set verbose Set 'verbose' mode. >>> hello Hello, how can I assist you today? total duration: 835.322625ms load duration: 452.875µs prompt eval count: 42 token(s) prompt eval duration: 593.785ms prompt eval rate: 70.73 tokens/s eval count: 10 token(s) eval duration: 240.374ms eval rate: 41.60 tokens/s llm library: metal GPU loaded layers: 1/27 >>> ``` The JSON payload: ```json { "model": "orca-mini", "created_at": "2024-01-23T20:23:02.168454Z", "response": " Hello, what can I assist you with today?", "done": true, "context": [ 31822, ... ], "total_duration": 849287875, "load_duration": 185542, "prompt_eval_count": 42, "prompt_eval_duration": 558791000, "eval_count": 11, "eval_duration": 290096000, "runtime": { "library": "metal", "layers": 1, "max_layers": 27 } } ``` --- <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 15:35:18 -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#21344
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?