github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6825] LLava:13B Model Outputting ############### After Period of Inactivity #50824

New Issue
Closed
opened 2026-04-28 17:12:56 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 17:12:56 -05:00
Owner
Copy Link

Originally created by @Atharvaaat on GitHub (Sep 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6825

What is the issue?

Description:

I encountered an issue with the Ollama LLava:13B model where the output was consistently ############### after a period of inactivity. Restarting the ollama.service resolved the issue temporarily, but the root cause remains unclear.

Environment:

  • Model: Ollama LLava:13B
  • System Specs:
    • OS: Debian (Google Cloud VM)
    • GPU: NVIDIA L4
    • Driver/CUDA: Latest drivers compatible with NVIDIA L4
    • Service: Ollama.service

Issue Details:

  1. I was testing the Ollama LLava:13B model without any issues for an extended session.
  2. After stopping the model for a period of time, when attempting to restart inference, the output was consistently ###############.
  3. Restarting the ollama.service resolved the issue temporarily, and normal functionality was restored.
  4. The root cause of the incorrect output (###############) is unknown and has not been encountered previously in continuous usage.

Steps to Reproduce:

  1. Start Ollama LLava:13B model on a Google Cloud VM with an NVIDIA L4 GPU.
  2. Perform inference operations successfully.
  3. Allow a period of inactivity (length uncertain, may be related to session timeout or resource deallocation).
  4. Resume inference, resulting in ############### as the output.
  5. Restart ollama.service to restore normal function.

Expected Behavior:

The model should resume normal operation after a period of inactivity, without needing to restart the service.

Observed Behavior:

After resuming inference post-inactivity, the model consistently output ############### until the service was restarted.

Additional Information:

  • Logs and model outputs prior to the issue were normal.
  • This behavior suggests a potential issue with resource management, memory, or session state handling in the model.

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.3.10

Originally created by @Atharvaaat on GitHub (Sep 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6825 ### What is the issue? **Description:** I encountered an issue with the Ollama LLava:13B model where the output was consistently `###############` after a period of inactivity. Restarting the `ollama.service` resolved the issue temporarily, but the root cause remains unclear. --- **Environment:** - **Model:** Ollama LLava:13B - **System Specs:** - **OS:** Debian (Google Cloud VM) - **GPU:** NVIDIA L4 - **Driver/CUDA:** Latest drivers compatible with NVIDIA L4 - **Service:** Ollama.service --- **Issue Details:** 1. I was testing the Ollama LLava:13B model without any issues for an extended session. 2. After stopping the model for a period of time, when attempting to restart inference, the output was consistently `###############`. 3. Restarting the `ollama.service` resolved the issue temporarily, and normal functionality was restored. 4. The root cause of the incorrect output (`###############`) is unknown and has not been encountered previously in continuous usage. --- **Steps to Reproduce:** 1. Start Ollama LLava:13B model on a Google Cloud VM with an NVIDIA L4 GPU. 2. Perform inference operations successfully. 3. Allow a period of inactivity (length uncertain, may be related to session timeout or resource deallocation). 4. Resume inference, resulting in `###############` as the output. 5. Restart `ollama.service` to restore normal function. --- **Expected Behavior:** The model should resume normal operation after a period of inactivity, without needing to restart the service. --- **Observed Behavior:** After resuming inference post-inactivity, the model consistently output `###############` until the service was restarted. --- **Additional Information:** - Logs and model outputs prior to the issue were normal. - This behavior suggests a potential issue with resource management, memory, or session state handling in the model. ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.3.10
GiteaMirror added the bug label 2026-04-28 17:12:56 -05:00
GiteaMirror commented 2026-04-28 17:12:57 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 16, 2024):

Server logs may help in debugging.

<!-- gh-comment-id:2352827227 --> @rick-github commented on GitHub (Sep 16, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may help in debugging.
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#50824
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?