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 #9435] [MERGED] ml/backend/ggml: consolidate system info logging #12962

New Issue
Closed
opened 2026-04-13 00:13:56 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:13:56 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/9435
Author: @mxyng
Created: 3/1/2025
Status: ✅ Merged
Merged: 3/4/2025
Merged by: @mxyng

Base: main ← Head: mxyng/device-logs

📝 Commits (1)

  • 6bbf94b ml/backend/ggml: consolidate system info logging

📊 Changes

7 files changed (+60 additions, -84 deletions)

View changed files

📝 cmd/cmd.go (+0 -2)
📝 llama/llama.go (+0 -25)
📝 ml/backend.go (+0 -1)
📝 ml/backend/ggml/ggml.go (+6 -53)
📝 ml/backend/ggml/ggml/src/ggml.go (+54 -0)
📝 runner/llamarunner/runner.go (+0 -1)
📝 runner/ollamarunner/runner.go (+0 -2)

📄 Description

Previously the log line describing available backends can be hard to read. Since devices and features are separated by : and |, it's hard to tell which features are associated with the device.

time=2025-03-01T03:23:55.895Z level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=8

Additionally, backends are enumerated by the order they're loaded which always puts the built-in backend first. Enumerating backends based on device is preferable since it's by priority (score).

vs. now

time=2025-03-01T03:18:04.270Z level=INFO source=ggml.go:140 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=860,890 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)

🔄 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/9435 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 3/1/2025 **Status:** ✅ Merged **Merged:** 3/4/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/device-logs` --- ### 📝 Commits (1) - [`6bbf94b`](https://github.com/ollama/ollama/commit/6bbf94b7e86fb5621eb9baa83f559cc0a81a6885) ml/backend/ggml: consolidate system info logging ### 📊 Changes **7 files changed** (+60 additions, -84 deletions) <details> <summary>View changed files</summary> 📝 `cmd/cmd.go` (+0 -2) 📝 `llama/llama.go` (+0 -25) 📝 `ml/backend.go` (+0 -1) 📝 `ml/backend/ggml/ggml.go` (+6 -53) 📝 `ml/backend/ggml/ggml/src/ggml.go` (+54 -0) 📝 `runner/llamarunner/runner.go` (+0 -1) 📝 `runner/ollamarunner/runner.go` (+0 -2) </details> ### 📄 Description Previously the log line describing available backends can be hard to read. Since devices and features are separated by `:` and `|`, it's hard to tell which features are associated with the device. ``` time=2025-03-01T03:23:55.895Z level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=8 ``` Additionally, backends are enumerated by the order they're loaded which always puts the built-in backend first. Enumerating backends based on device is preferable since it's by priority (score). vs. now ``` time=2025-03-01T03:18:04.270Z level=INFO source=ggml.go:140 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=860,890 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) ``` --- <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 2026-04-13 00:13:57 -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#12962
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?