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 #7033] Using smaller context size shows CUDA error: CUBLAS_STATUS_NOT_INITIALIZED #30220

New Issue
Closed
opened 2026-04-22 09:44:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 09:44:52 -05:00
Owner
Copy Link

Originally created by @aamsur-933 on GitHub (Sep 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7033

What is the issue?

Helo, i have PC with NVIDIA 10GB Vram, i have installed ollama and deepseek-coder-v2:16b model on it, i will use continue.dev in my vscode to communicate with ollama.

i have problem when i set ctx size in the plugin to 4K like so "contextLength": 4096, with deepseek-coder-v2:16b i got CUDA error: CUBLAS_STATUS_NOT_INITIALIZED in ollama logs.
here is the logs from ollama:
ctx-4k.log

but, when i set bigger ctx size to 32K in the plugin like so "contextLength": 32768, the model will running without any error.
Screenshot from 2024-09-29 17-11-30
here is the logs:
ctx-32k.log

Is there any problem with my env?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.12

Originally created by @aamsur-933 on GitHub (Sep 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7033 ### What is the issue? Helo, i have PC with NVIDIA 10GB Vram, i have installed ollama and **deepseek-coder-v2:16b** model on it, i will use continue.dev in my vscode to communicate with ollama. i have problem when i set ctx size in the plugin to 4K like so `"contextLength": 4096, ` with deepseek-coder-v2:16b i got `CUDA error: CUBLAS_STATUS_NOT_INITIALIZED` in ollama logs. here is the logs from ollama: [ctx-4k.log](https://github.com/user-attachments/files/17178823/ctx-4k.log) but, when i set bigger ctx size to 32K in the plugin like so `"contextLength": 32768, ` the model will running without any error. ![Screenshot from 2024-09-29 17-11-30](https://github.com/user-attachments/assets/c3f2cbef-a2c8-4443-93e0-62d3db467847) here is the logs: [ctx-32k.log](https://github.com/user-attachments/files/17178843/ctx-32k.log) Is there any problem with my env? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.12
GiteaMirror added the bug label 2026-04-22 09:44:52 -05:00
GiteaMirror commented 2026-04-22 09:44:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 29, 2024):

https://github.com/ollama/ollama/issues/6715#issuecomment-2339278048

<!-- gh-comment-id:2381303205 --> @rick-github commented on GitHub (Sep 29, 2024): https://github.com/ollama/ollama/issues/6715#issuecomment-2339278048
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#30220
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?