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 #12150] "/api/genterate" error with granite3.3:2b since 0.11.5 when using OLLAMA_MULTIUSER_CACHE=1 #70138

New Issue
Open
opened 2026-05-04 20:29:15 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 20:29:15 -05:00
Owner
Copy Link

Originally created by @ChristianAnkeZ1 on GitHub (Sep 2, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12150

What is the issue?

I am using the api to generate a response with the granite3.3:2b model. Since ollama 0.11.5 i got this server error:

an error was encountered while running the model: GGML_ASSERT(is_full && \"seq_cp() is only supported for full KV buffers\") failed

0.11.4 works fine.

I run fully on CPU in a docker container and the following environment variables are set:

HTTP_PROXY=:3128
HTTPS_PROXY=:3128
NO_PROXY=
OLLAMA_KEEP_ALIVE=30m
OLLAMA_NUM_PARALLEL=2
OLLAMA_MAX_LOADED_MODELS=2
OLLAMA_FLASH_ATTENTION=1
OLLAMA_NEW_ESTIMATES=0
OLLAMA_DEBUG=1
OLLAMA_LOAD_TIMEOUT=90m
OLLAMA_MULTIUSER_CACHE=1
OLLAMA_CONTEXT_LENGTH=8096
OLLAMA_ORIGINS=

Disabling OLLAMA_MULTIUSER_CACHE will make it work again.

ollama-error.log.txt

Relevant log output

OS

Linux

GPU

No response

CPU

AMD

Ollama version

0.11.5

Originally created by @ChristianAnkeZ1 on GitHub (Sep 2, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12150 ### What is the issue? I am using the api to generate a response with the granite3.3:2b model. Since ollama 0.11.5 i got this server error: ``` an error was encountered while running the model: GGML_ASSERT(is_full && \"seq_cp() is only supported for full KV buffers\") failed ``` 0.11.4 works fine. I run fully on CPU in a docker container and the following environment variables are set: HTTP_PROXY=<myproxy>:3128 HTTPS_PROXY=<myproxy>:3128 NO_PROXY=<some-exceptions> OLLAMA_KEEP_ALIVE=30m OLLAMA_NUM_PARALLEL=2 OLLAMA_MAX_LOADED_MODELS=2 OLLAMA_FLASH_ATTENTION=1 OLLAMA_NEW_ESTIMATES=0 OLLAMA_DEBUG=1 OLLAMA_LOAD_TIMEOUT=90m OLLAMA_MULTIUSER_CACHE=1 OLLAMA_CONTEXT_LENGTH=8096 OLLAMA_ORIGINS=<some-origins> Disabling OLLAMA_MULTIUSER_CACHE will make it work again. [ollama-error.log.txt](https://github.com/user-attachments/files/22091381/ollama-error.log.txt) ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU AMD ### Ollama version 0.11.5
GiteaMirror added the bug label 2026-05-04 20:29:15 -05:00
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#70138
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?