github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4334] Error: llama runner process has terminated: exit status 0xc0000005 #28457

New Issue
Closed
opened 2026-04-22 06:39:01 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 06:39:01 -05:00
Owner
Copy Link

Originally created by @EthanScully on GitHub (May 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4334

What is the issue?

at the start of loading a model on v0.1.35, it errors out Error: llama runner process has terminated: exit status 0xc0000005
v0.1.34 works perfectly fine
log:

time=2024-05-10T22:52:42.838-04:00 level=ERROR source=sched.go:339 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000005 "
[GIN] 2024/05/10 - 22:52:42 | 500 |    2.7650401s |       127.0.0.1 | POST     "/api/chat"
time=2024-05-10T22:52:48.161-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.3231542
time=2024-05-10T22:52:48.488-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.6501493
time=2024-05-10T22:52:48.832-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.9940694

using the AMD Radeon RX 6800
windows 11 and latest drivers

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

v0.1.35

Originally created by @EthanScully on GitHub (May 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4334 ### What is the issue? at the start of loading a model on v0.1.35, it errors out `Error: llama runner process has terminated: exit status 0xc0000005` v0.1.34 works perfectly fine log: ``` time=2024-05-10T22:52:42.838-04:00 level=ERROR source=sched.go:339 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000005 " [GIN] 2024/05/10 - 22:52:42 | 500 | 2.7650401s | 127.0.0.1 | POST "/api/chat" time=2024-05-10T22:52:48.161-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.3231542 time=2024-05-10T22:52:48.488-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.6501493 time=2024-05-10T22:52:48.832-04:00 level=WARN source=sched.go:507 msg="gpu VRAM usage didn't recover within timeout" seconds=5.9940694 ``` using the AMD Radeon RX 6800 windows 11 and latest drivers ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version v0.1.35
GiteaMirror added the bug label 2026-04-22 06:39:01 -05:00
GiteaMirror commented 2026-04-22 06:39:03 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 11, 2024):

This should be fixed in https://github.com/ollama/ollama/releases/tag/v0.1.36, sorry about this!

<!-- gh-comment-id:2105606442 --> @jmorganca commented on GitHub (May 11, 2024): This should be fixed in https://github.com/ollama/ollama/releases/tag/v0.1.36, sorry about this!
GiteaMirror commented 2026-04-22 06:39:03 -05:00
Author
Owner
Copy Link

@seraasch commented on GitHub (May 11, 2024):

I just got this error with v0.1.36
AMD RX 7800 XT

<!-- gh-comment-id:2106028743 --> @seraasch commented on GitHub (May 11, 2024): I just got this error with v0.1.36 AMD RX 7800 XT
GiteaMirror commented 2026-04-22 06:39:04 -05:00
Author
Owner
Copy Link

@ReOT20 commented on GitHub (May 13, 2024):

This should be fixed in https://github.com/ollama/ollama/releases/tag/v0.1.36, sorry about this!

Same problem on linux and 0.1.37 with 5700 XT masked as gfx1030.

Here is additional info from the logs that could be helpful:
:0:rocdevice.cpp :2726: 846396226165 us: [pid:171202 tid:0x7f2f46a006c0] Callback: Queue 0x7f2e28700000 aborting with error : HSA_STATUS_ERROR_MEMORY_APERTURE_VIOLATION: The agent attempted to access memory beyond the largest legal address. code: 0x29

<!-- gh-comment-id:2108506979 --> @ReOT20 commented on GitHub (May 13, 2024): > This should be fixed in https://github.com/ollama/ollama/releases/tag/v0.1.36, sorry about this! Same problem on linux and 0.1.37 with 5700 XT masked as gfx1030. Here is additional info from the logs that could be helpful: `:0:rocdevice.cpp :2726: 846396226165 us: [pid:171202 tid:0x7f2f46a006c0] Callback: Queue 0x7f2e28700000 aborting with error : HSA_STATUS_ERROR_MEMORY_APERTURE_VIOLATION: The agent attempted to access memory beyond the largest legal address. code: 0x29 `
GiteaMirror commented 2026-04-22 06:39:05 -05:00
Author
Owner
Copy Link

@V01D-NULL commented on GitHub (May 27, 2024):

I'm seeing this on 0.1.38

<!-- gh-comment-id:2134139386 --> @V01D-NULL commented on GitHub (May 27, 2024): I'm seeing this on 0.1.38
GiteaMirror commented 2026-04-22 06:39:06 -05:00
Author
Owner
Copy Link

@Codesbyusman commented on GitHub (Jun 19, 2024):

facing same issue when trying to run codegemma

ollama run codegemma

Error: llama runner process has terminated: exit status 0xc0000005

ollama version = 0.1.41

any help in this regard?

<!-- gh-comment-id:2177790028 --> @Codesbyusman commented on GitHub (Jun 19, 2024): facing same issue when trying to run codegemma `ollama run codegemma` > Error: llama runner process has terminated: exit status 0xc0000005 ollama version = 0.1.41 any help in this regard?
GiteaMirror commented 2026-04-22 06:39:06 -05:00
Author
Owner
Copy Link

@antibyte commented on GitHub (Jun 22, 2024):

same here

<!-- gh-comment-id:2184124770 --> @antibyte commented on GitHub (Jun 22, 2024): same here
GiteaMirror commented 2026-04-22 06:39:07 -05:00
Author
Owner
Copy Link

@Codesbyusman commented on GitHub (Jun 24, 2024):

@antibyte update ollama to 0.1.45, it's working there

<!-- gh-comment-id:2185420988 --> @Codesbyusman commented on GitHub (Jun 24, 2024): @antibyte update ollama to 0.1.45, it's working there
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#28457
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?