github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8549] error: unsupported op 'CPY' #52028

New Issue
Closed
opened 2026-04-28 21:41:42 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 21:41:42 -05:00
Owner
Copy Link

Originally created by @devlux76 on GitHub (Jan 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8549

What is the issue?

I keep getting crashes on various vision models. This one is from the MiniCPM-V 2.6 straight off ollama

time=2025-01-23T07:51:20.484-07:00 level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=3390 keep=4 new=2048
time=2025-01-23T07:51:20.484-07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=2048 used=0 remaining=2048
time=2025-01-23T07:51:29.549-07:00 level=DEBUG source=cache.go:231 msg="context limit hit - shifting" id=0 limit=2048 input=2048 keep=4 discard=1022
ggml_metal_encode_node: error: unsupported op 'CPY'
ggml-metal_darwin_arm64.m:1292: unsupported op
SIGABRT: abort
PC=0x19b6eb720 m=5 sigcode=0
signal arrived during cgo execution

Seems to do thesame thing on Llama 3.2 Vision as well, but then it says the unsupported op is ROPE when crashing in the same place.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.7

Originally created by @devlux76 on GitHub (Jan 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8549 ### What is the issue? I keep getting crashes on various vision models. This one is from the MiniCPM-V 2.6 straight off ollama ``` time=2025-01-23T07:51:20.484-07:00 level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=3390 keep=4 new=2048 time=2025-01-23T07:51:20.484-07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=2048 used=0 remaining=2048 time=2025-01-23T07:51:29.549-07:00 level=DEBUG source=cache.go:231 msg="context limit hit - shifting" id=0 limit=2048 input=2048 keep=4 discard=1022 ggml_metal_encode_node: error: unsupported op 'CPY' ggml-metal_darwin_arm64.m:1292: unsupported op SIGABRT: abort PC=0x19b6eb720 m=5 sigcode=0 signal arrived during cgo execution ``` Seems to do thesame thing on Llama 3.2 Vision as well, but then it says the unsupported op is ROPE when crashing in the same place. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-28 21:41:42 -05:00
GiteaMirror commented 2026-04-28 21:41:45 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Jan 24, 2025):

Do you have KV cache quantization enabled? If so, this is the same as #7938

<!-- gh-comment-id:2611382206 --> @jessegross commented on GitHub (Jan 24, 2025): Do you have KV cache quantization enabled? If so, this is the same as #7938
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#52028
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?