github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2189] Error: Post "http://127.0.0.1:11434/api/generate": EOF #47763

New Issue
Closed
opened 2026-04-28 05:15:29 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 05:15:29 -05:00
Owner
Copy Link

Originally created by @blackandcold on GitHub (Jan 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2189

Installed by script and not AUR, previously running fine but since 2 weeks I can't run it anymore. MacOS 0.1.20 works fine.

ollama run llama2:latest
Error: Post "http://127.0.0.1:11434/api/generate": EOF

System:
OS: EndeavourOS Linux x86_64
Kernel: 6.7.0-arch3-1
Shell: zsh 5.9
CPU: AMD Ryzen 9 5900X (24) @ 3.700GHz
GPU: AMD ATI Radeon RX 6800 16GB
Memory: 13639MiB / 128714MiB

So there is some free action on a null pointer? :)

Jän 25 15:58:43 OS ollama[192151]: 2024/01/25 15:58:43 gpu.go:104: Radeon GPU detected
Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 33.771µs | 127.0.0.1 | HEAD ">
Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 2.403459ms | 127.0.0.1 | POST ">
Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 771.286µs | 127.0.0.1 | POST ">
Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 shim_ext_server_linux.go:24: Updating PATH to /usr/local/sbi>
Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 shim_ext_server.go:92: Loading Dynamic Shim llm server: /tmp>
Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 ext_server_common.go:136: Initializing internal llama server
Jän 25 15:59:27 OS ollama[192151]: free(): invalid pointer
Jän 25 15:59:27 OS systemd[1]: ollama.service: Main process exited, code=dumped, status=6/ABRT
Jän 25 15:59:27 OS systemd[1]: ollama.service: Failed with result 'core-dump'.
Jän 25 15:59:27 OS systemd[1]: ollama.service: Consumed 1.181s CPU time, 406.9M memory peak, 0B memory swap peak.
Jän 25 15:59:31 OS systemd[1]: ollama.service: Scheduled restart job, restart counter is at 2.
Jän 25 15:59:31 OS systemd[1]: Started Ollama Service.
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 images.go:808: total blobs: 24
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 images.go:815: total unused blobs removed: 0
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 routes.go:930: Listening on 127.0.0.1:11434 (version 0.1.20)
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 shim_ext_server.go:142: Dynamic LLM variants [cuda rocm]
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:88: Detecting GPU type
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:203: Searching for GPU management library libnvidia-m>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:248: Discovered GPU libraries: [/usr/lib/libnvidia-ml>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:259: Unable to load CUDA management library /usr/lib/>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:259: Unable to load CUDA management library /usr/lib6>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:203: Searching for GPU management library librocm_smi>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:248: Discovered GPU libraries: [/opt/rocm/lib/librocm>
Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:104: Radeon GPU detected

Originally created by @blackandcold on GitHub (Jan 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2189 Installed by script and not AUR, previously running fine but since 2 weeks I can't run it anymore. MacOS 0.1.20 works fine. > ollama run llama2:latest > Error: Post "http://127.0.0.1:11434/api/generate": EOF System: OS: EndeavourOS Linux x86_64 Kernel: 6.7.0-arch3-1 Shell: zsh 5.9 CPU: AMD Ryzen 9 5900X (24) @ 3.700GHz GPU: AMD ATI Radeon RX 6800 16GB Memory: 13639MiB / 128714MiB So there is some free action on a null pointer? :) > Jän 25 15:58:43 OS ollama[192151]: 2024/01/25 15:58:43 gpu.go:104: Radeon GPU detected > Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 33.771µs | 127.0.0.1 | HEAD "> > Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 2.403459ms | 127.0.0.1 | POST "> > Jän 25 15:59:26 OS ollama[192151]: [GIN] 2024/01/25 - 15:59:26 | 200 | 771.286µs | 127.0.0.1 | POST "> > Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 shim_ext_server_linux.go:24: Updating PATH to /usr/local/sbi> > Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 shim_ext_server.go:92: Loading Dynamic Shim llm server: /tmp> > Jän 25 15:59:27 OS ollama[192151]: 2024/01/25 15:59:27 ext_server_common.go:136: Initializing internal llama server > **Jän 25 15:59:27 OS ollama[192151]: free(): invalid pointer** > Jän 25 15:59:27 OS systemd[1]: ollama.service: Main process exited, code=dumped, status=6/ABRT > Jän 25 15:59:27 OS systemd[1]: ollama.service: Failed with result 'core-dump'. > Jän 25 15:59:27 OS systemd[1]: ollama.service: Consumed 1.181s CPU time, 406.9M memory peak, 0B memory swap peak. > Jän 25 15:59:31 OS systemd[1]: ollama.service: Scheduled restart job, restart counter is at 2. > Jän 25 15:59:31 OS systemd[1]: Started Ollama Service. > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 images.go:808: total blobs: 24 > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 images.go:815: total unused blobs removed: 0 > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 routes.go:930: Listening on 127.0.0.1:11434 (version 0.1.20) > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 shim_ext_server.go:142: Dynamic LLM variants [cuda rocm] > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:88: Detecting GPU type > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:203: Searching for GPU management library libnvidia-m> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:248: Discovered GPU libraries: [/usr/lib/libnvidia-ml> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:259: Unable to load CUDA management library /usr/lib/> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:259: Unable to load CUDA management library /usr/lib6> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:203: Searching for GPU management library librocm_smi> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:248: Discovered GPU libraries: [/opt/rocm/lib/librocm> > Jän 25 15:59:31 OS ollama[192251]: 2024/01/25 15:59:31 gpu.go:104: Radeon GPU detected
GiteaMirror commented 2026-04-28 05:15:30 -05:00
Author
Owner
Copy Link

@blackandcold commented on GitHub (Jan 25, 2024):

For whatever reason starting ollama manually works, just not with systemd.
Have to investigate what happened there but seems it is not a ollama problem, closing.

<!-- gh-comment-id:1910407932 --> @blackandcold commented on GitHub (Jan 25, 2024): For whatever reason starting ollama manually works, just not with systemd. Have to investigate what happened there but seems it is not a ollama problem, closing.
GiteaMirror commented 2026-04-28 05:15:32 -05:00
Author
Owner
Copy Link

@blackandcold commented on GitHub (Jan 25, 2024):

Ok downloading a new model works, not running it!

2024/01/25 16:13:17 shim_ext_server_linux.go:24: Updating PATH to /usr/local/sbin:/usr/local/bin:/usr/bin:/opt/cuda/bin:/opt/cuda/nsight_compute:/opt/cuda/nsight_systems/bin:/usr/lib/jvm/default/bin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl:/tmp/ollama268014040/rocm
Lazy loading /tmp/ollama268014040/rocm/libext_server.so library
2024/01/25 16:13:17 shim_ext_server.go:92: Loading Dynamic Shim llm server: /tmp/ollama268014040/rocm/libext_server.so
2024/01/25 16:13:17 ext_server_common.go:136: Initializing internal llama server
free(): invalid pointer
[1] 193968 IOT instruction (core dumped) ollama serve

<!-- gh-comment-id:1910409756 --> @blackandcold commented on GitHub (Jan 25, 2024): Ok downloading a new model works, not running it! 2024/01/25 16:13:17 shim_ext_server_linux.go:24: Updating PATH to /usr/local/sbin:/usr/local/bin:/usr/bin:/opt/cuda/bin:/opt/cuda/nsight_compute:/opt/cuda/nsight_systems/bin:/usr/lib/jvm/default/bin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl:/tmp/ollama268014040/rocm Lazy loading /tmp/ollama268014040/rocm/libext_server.so library 2024/01/25 16:13:17 shim_ext_server.go:92: Loading Dynamic Shim llm server: /tmp/ollama268014040/rocm/libext_server.so 2024/01/25 16:13:17 ext_server_common.go:136: Initializing internal llama server free(): invalid pointer [1] 193968 IOT instruction (core dumped) ollama serve
GiteaMirror commented 2026-04-28 05:15:35 -05:00
Author
Owner
Copy Link

@blackandcold commented on GitHub (Jan 25, 2024):

And here we have the exact error already open:
https://github.com/ollama/ollama/issues/2165

<!-- gh-comment-id:1910411420 --> @blackandcold commented on GitHub (Jan 25, 2024): And here we have the exact error already open: https://github.com/ollama/ollama/issues/2165
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
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#47763
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?