github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8492] ollama + deepseek-v2 SIGSEGV: segmentation violation #5470

New Issue
Closed
opened 2026-04-12 16:42:04 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:42:04 -05:00
Owner
Copy Link

Originally created by @jonsen on GitHub (Jan 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8492

What is the issue?

Here are ollama output log:

llama_model_load: vocab only - skipping tensors
llama.cpp:11968: The current context does not support K-shift
SIGSEGV: segmentation violation
PC=0x7f87e284d1d7 m=0 sigcode=1 addr=0x206403fd8
signal arrived during cgo execution

goroutine 4 gp=0xc0000076c0 m=0 mp=0x55ef197e41c0 [syscall]:
runtime.cgocall(0x55ef191fcfb0, 0xc00014aba0)
runtime/cgocall.go:167 +0x4b fp=0xc00014ab78 sp=0xc00014ab40 pc=0x55ef18fb14eb
github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f876cc0c7b0, {0x1, 0x7f876caf4fc0, 0x0, 0x0, 0x7f876caf6fd0, 0x7f876caf8fe0, 0x7f876cd45130, 0x7f876f513e80})
_cgo_gotypes.go:556 +0x4f fp=0xc00014aba0 sp=0xc00014ab78 pc=0x55ef1905b56f
github.com/ollama/ollama/llama.(*Context).Decode.func1(0x55ef191f86eb?, 0x7f876cc0c7b0?)
github.com/ollama/ollama/llama/llama.go:207 +0xf5 fp=0xc00014ac90 sp=0xc00014aba0 pc=0x55ef1905dd95
github.com/ollama/ollama/llama.(*Context).Decode(0x55ef19888320?, 0x0?)
github.com/ollama/ollama/llama/llama.go:207 +0x13 fp=0xc00014acd8 sp=0xc00014ac90 pc=0x55ef1905dc13
github.com/ollama/ollama/llama/runner.(*Server).processBatch(0xc0000d2000, 0xc0002a61e0, 0xc00014af20)
github.com/ollama/ollama/llama/runner/runner.go:434 +0x23f fp=0xc00014aee0 sp=0xc00014acd8 pc=0x55ef191f74df
github.com/ollama/ollama/llama/runner.(*Server).run(0xc0000d2000, {0x55ef195f80c0, 0xc0000d0050})
github.com/ollama/ollama/llama/runner/runner.go:342 +0x1d5 fp=0xc00014afb8 sp=0xc00014aee0 pc=0x55ef191f6f15
github.com/ollama/ollama/llama/runner.Execute.gowrap2()
github.com/ollama/ollama/llama/runner/runner.go:975 +0x28 fp=0xc00014afe0 sp=0xc00014afb8 pc=0x55ef191fbe08
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00014afe8 sp=0xc00014afe0 pc=0x55ef18fbef21
created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1
github.com/ollama/ollama/llama/runner/runner.go:975 +0xde5

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.5,0.5.7

Originally created by @jonsen on GitHub (Jan 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8492 ### What is the issue? Here are ollama output log: llama_model_load: vocab only - skipping tensors llama.cpp:11968: The current context does not support K-shift SIGSEGV: segmentation violation PC=0x7f87e284d1d7 m=0 sigcode=1 addr=0x206403fd8 signal arrived during cgo execution goroutine 4 gp=0xc0000076c0 m=0 mp=0x55ef197e41c0 [syscall]: runtime.cgocall(0x55ef191fcfb0, 0xc00014aba0) runtime/cgocall.go:167 +0x4b fp=0xc00014ab78 sp=0xc00014ab40 pc=0x55ef18fb14eb github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f876cc0c7b0, {0x1, 0x7f876caf4fc0, 0x0, 0x0, 0x7f876caf6fd0, 0x7f876caf8fe0, 0x7f876cd45130, 0x7f876f513e80}) _cgo_gotypes.go:556 +0x4f fp=0xc00014aba0 sp=0xc00014ab78 pc=0x55ef1905b56f github.com/ollama/ollama/llama.(*Context).Decode.func1(0x55ef191f86eb?, 0x7f876cc0c7b0?) github.com/ollama/ollama/llama/llama.go:207 +0xf5 fp=0xc00014ac90 sp=0xc00014aba0 pc=0x55ef1905dd95 github.com/ollama/ollama/llama.(*Context).Decode(0x55ef19888320?, 0x0?) github.com/ollama/ollama/llama/llama.go:207 +0x13 fp=0xc00014acd8 sp=0xc00014ac90 pc=0x55ef1905dc13 github.com/ollama/ollama/llama/runner.(*Server).processBatch(0xc0000d2000, 0xc0002a61e0, 0xc00014af20) github.com/ollama/ollama/llama/runner/runner.go:434 +0x23f fp=0xc00014aee0 sp=0xc00014acd8 pc=0x55ef191f74df github.com/ollama/ollama/llama/runner.(*Server).run(0xc0000d2000, {0x55ef195f80c0, 0xc0000d0050}) github.com/ollama/ollama/llama/runner/runner.go:342 +0x1d5 fp=0xc00014afb8 sp=0xc00014aee0 pc=0x55ef191f6f15 github.com/ollama/ollama/llama/runner.Execute.gowrap2() github.com/ollama/ollama/llama/runner/runner.go:975 +0x28 fp=0xc00014afe0 sp=0xc00014afb8 pc=0x55ef191fbe08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00014afe8 sp=0xc00014afe0 pc=0x55ef18fbef21 created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1 github.com/ollama/ollama/llama/runner/runner.go:975 +0xde5 ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.5,0.5.7
GiteaMirror added the bug label 2026-04-12 16:42:04 -05:00
GiteaMirror commented 2026-04-12 16:42:05 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 20, 2025):

https://github.com/ollama/ollama/issues/5975

<!-- gh-comment-id:2601853585 --> @rick-github commented on GitHub (Jan 20, 2025): https://github.com/ollama/ollama/issues/5975
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#5470
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?