github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #11278] [MERGED] mimic logs for layers on new engine #39369

New Issue
Closed
opened 2026-04-23 00:06:46 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-23 00:06:46 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11278
Author: @dhiltgen
Created: 7/2/2025
Status: ✅ Merged
Merged: 7/2/2025
Merged by: @dhiltgen

Base: main ← Head: logs

📝 Commits (1)

  • 1e6d5d8 mimic logs for layers on new engine

📊 Changes

1 file changed (+18 additions, -0 deletions)

View changed files

📝 ml/backend/ggml/ggml.go (+18 -0)

📄 Description

This adds some extra logs to make the new engine a bit more consistent with the llama engine.

I opted not to change the 2 existing lines showing buffer sizes since they're close enough.

Example from llama engine:

load_tensors: offloading 28 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 29/29 layers to GPU
load_tensors:   CPU_Mapped model buffer size =   308.23 MiB
load_tensors: Metal_Mapped model buffer size =  1918.36 MiB

With this change, same model on the new engine

time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:362 msg="offloading 28 repeating layers to GPU"
time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:368 msg="offloading output layer to GPU"
time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:378 msg="offloaded 29/29 layers to GPU"
time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:380 msg="model weights" buffer=Metal size="1.9 GiB"
time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:380 msg="model weights" buffer=CPU size="308.2 MiB"

🔄 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/11278 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 7/2/2025 **Status:** ✅ Merged **Merged:** 7/2/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `logs` --- ### 📝 Commits (1) - [`1e6d5d8`](https://github.com/ollama/ollama/commit/1e6d5d844282d8b11545870f2ccccc9f4355a5cc) mimic logs for layers on new engine ### 📊 Changes **1 file changed** (+18 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `ml/backend/ggml/ggml.go` (+18 -0) </details> ### 📄 Description This adds some extra logs to make the new engine a bit more consistent with the llama engine. I opted not to change the 2 existing lines showing buffer sizes since they're close enough. Example from llama engine: ``` load_tensors: offloading 28 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 29/29 layers to GPU load_tensors: CPU_Mapped model buffer size = 308.23 MiB load_tensors: Metal_Mapped model buffer size = 1918.36 MiB ``` With this change, same model on the new engine ``` time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:362 msg="offloading 28 repeating layers to GPU" time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:368 msg="offloading output layer to GPU" time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:378 msg="offloaded 29/29 layers to GPU" time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:380 msg="model weights" buffer=Metal size="1.9 GiB" time=2025-07-02T16:16:54.727-07:00 level=INFO source=ggml.go:380 msg="model weights" buffer=CPU size="308.2 MiB" ``` --- <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 2026-04-23 00:06:46 -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#39369
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?