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

[GH-ISSUE #12886] ollama 0.12.[78] not using AVX in non-GPU situations #70599

New Issue
Closed
opened 2026-05-04 22:12:37 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 22:12:37 -05:00
Owner
Copy Link

Originally created by @rick-github on GitHub (Oct 31, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12886

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

$ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.6 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b
⠸ time=2025-10-31T15:24:39.908Z level=INFO source=ggml.go:104 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.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)

$ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.7 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b ''
⠹ time=2025-10-31T15:26:24.078Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

$ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.8 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b ''
⠹ time=2025-10-31T15:26:57.214Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

$ docker run -p 11111:11434 --gpus all -v ~/.ollama:/root/.ollama ollama/ollama:0.12.8 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b ''
⠼ time=2025-10-31T15:44:30.705Z level=INFO source=ggml.go:104 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.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)

git bisect shows the behaviour changed with 3258a89b6e

$ git bisect good
3258a89b6e4c2030ca47dfe51483e768cbd38b33 is the first bad commit
commit 3258a89b6e4c2030ca47dfe51483e768cbd38b33
Author: Daniel Hiltgen <dhiltgen@users.noreply.github.com>
Date:   Thu Oct 23 11:20:02 2025 -0700

    DRY out the runner lifecycle code (#12540)

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @rick-github on GitHub (Oct 31, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12886 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? ```console $ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.6 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b ⠸ time=2025-10-31T15:24:39.908Z level=INFO source=ggml.go:104 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.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) ``` ```console $ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.7 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b '' ⠹ time=2025-10-31T15:26:24.078Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ``` ```console $ docker run -p 11111:11434 -v ~/.ollama:/root/.ollama ollama/ollama:0.12.8 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b '' ⠹ time=2025-10-31T15:26:57.214Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ``` ```console $ docker run -p 11111:11434 --gpus all -v ~/.ollama:/root/.ollama ollama/ollama:0.12.8 2>&1 | grep cgo & sleep 2; OLLAMA_HOST=:11111 ollama run qwen2.5:0.5b '' ⠼ time=2025-10-31T15:44:30.705Z level=INFO source=ggml.go:104 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.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) ``` `git bisect` shows the behaviour changed with https://github.com/ollama/ollama/commit/3258a89b6e4c2030ca47dfe51483e768cbd38b33 ```console $ git bisect good 3258a89b6e4c2030ca47dfe51483e768cbd38b33 is the first bad commit commit 3258a89b6e4c2030ca47dfe51483e768cbd38b33 Author: Daniel Hiltgen <dhiltgen@users.noreply.github.com> Date: Thu Oct 23 11:20:02 2025 -0700 DRY out the runner lifecycle code (#12540) ``` ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 22:12:37 -05:00
GiteaMirror commented 2026-05-04 22:13:00 -05:00
Author
Owner
Copy Link

@maternion commented on GitHub (Oct 31, 2025):

So it is an issue from 0.12.7 onwards. Good to know, I reverted back for now, so no qwen3vl.

<!-- gh-comment-id:3473832943 --> @maternion commented on GitHub (Oct 31, 2025): So it is an issue from 0.12.7 onwards. Good to know, I reverted back for now, so no qwen3vl.
GiteaMirror commented 2026-05-04 22:13:01 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 31, 2025):

Fix will be in 0.12.9

<!-- gh-comment-id:3474975178 --> @dhiltgen commented on GitHub (Oct 31, 2025): Fix will be in 0.12.9
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 bug
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#70599
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?