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 #11157] ollama : Error: POST predict: Post "http://127.0.0.1:43799/completion": EOF #7359

New Issue
Closed
opened 2026-04-12 19:24:51 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 19:24:51 -05:00
Owner
Copy Link

Originally created by @nPrevail on GitHub (Jun 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11157

What is the issue?

When you run ollama run <LLM Module>, and if you input anything, you'll receive the following output when running a LLM:

Error: POST predict: Post "http://127.0.0.1:43799/completion": EOF

Relevant log output

Error: POST predict: Post "http://127.0.0.1:43799/completion": EOF

Server log:
https://pastebin.com/G6whWmkZ

server_debug_ollama.txt

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.7.0

Originally created by @nPrevail on GitHub (Jun 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11157 ### What is the issue? When you run `ollama run <LLM Module>`, and if you input anything, you'll receive the following output when running a LLM: `Error: POST predict: Post "http://127.0.0.1:43799/completion": EOF` ### Relevant log output ```shell Error: POST predict: Post "http://127.0.0.1:43799/completion": EOF ``` Server log: https://pastebin.com/G6whWmkZ [server_debug_ollama.txt](https://github.com/user-attachments/files/20958784/server_debug_ollama.txt) ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.7.0
GiteaMirror added the bug label 2026-04-12 19:24:51 -05:00
GiteaMirror commented 2026-04-12 19:24:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 21, 2025):

Server logs will aid in debugging.

<!-- gh-comment-id:2993752725 --> @rick-github commented on GitHub (Jun 21, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.
GiteaMirror commented 2026-04-12 19:24:58 -05:00
Author
Owner
Copy Link

@jaypeche commented on GitHub (Jun 22, 2025):

Same problem, just align versions of nvidia-cuda-toolkit && nvidia-drivers, with same ~amd64 keywording !

Recompile ollama from sources ebuild, using same cuda compiler.

This result a good execution of LLMs like mistral-nemo, with maximal GPU/CPU capabilities !

A feedback be interested, for AMD ROCm. I don't have AMD compatible machine for tests :;)

<!-- gh-comment-id:2994320716 --> @jaypeche commented on GitHub (Jun 22, 2025): Same problem, just align versions of nvidia-cuda-toolkit && nvidia-drivers, with same ~amd64 keywording ! Recompile ollama from sources ebuild, using same cuda compiler. This result a good execution of LLMs like mistral-nemo, with maximal GPU/CPU capabilities ! A feedback be interested, for AMD ROCm. I don't have AMD compatible machine for tests :;)
GiteaMirror commented 2026-04-12 19:24:59 -05:00
Author
Owner
Copy Link

@nPrevail commented on GitHub (Jun 28, 2025):

I've added the server log:
https://pastebin.com/G6whWmkZ

@rick-github

<!-- gh-comment-id:3014921679 --> @nPrevail commented on GitHub (Jun 28, 2025): I've added the server log: https://pastebin.com/G6whWmkZ @rick-github
GiteaMirror commented 2026-04-12 19:25:00 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 28, 2025):

Jun 27 21:28:08 nixos ollama[1266]: ggml_cuda_compute_forward: RMS_NORM failed
Jun 27 21:28:08 nixos ollama[1266]: ROCm error: no kernel image is available for execution on the device
Jun 27 21:28:08 nixos ollama[1266]:   current device: 0, in function ggml_cuda_compute_forward at /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2362
Jun 27 21:28:08 nixos ollama[1266]:   err
Jun 27 21:28:08 nixos ollama[1266]: /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: ROCm error
Jun 27 21:28:08 nixos ollama[1266]: Memory critical error by agent node-0 (Agent handle: 0x2e408890) on address 0x7fa97c200000. Reason: Memory in use.

Looks like the same as #11123

<!-- gh-comment-id:3015180091 --> @rick-github commented on GitHub (Jun 28, 2025): ``` Jun 27 21:28:08 nixos ollama[1266]: ggml_cuda_compute_forward: RMS_NORM failed Jun 27 21:28:08 nixos ollama[1266]: ROCm error: no kernel image is available for execution on the device Jun 27 21:28:08 nixos ollama[1266]: current device: 0, in function ggml_cuda_compute_forward at /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2362 Jun 27 21:28:08 nixos ollama[1266]: err Jun 27 21:28:08 nixos ollama[1266]: /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: ROCm error Jun 27 21:28:08 nixos ollama[1266]: Memory critical error by agent node-0 (Agent handle: 0x2e408890) on address 0x7fa97c200000. Reason: Memory in use. ``` Looks like the same as #11123
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#7359
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?