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 #2303] Large number of images causes hanging/error #47840

New Issue
Closed
opened 2026-04-28 05:28:02 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 05:28:02 -05:00
Owner
Copy Link

Originally created by @jmorganca on GitHub (Feb 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2303

If submitting too many images via the images API parameter in /api/generate or /api/chat

[1706759134] slot 0 - loaded image
[1706759135] slot 0 - loaded image
[1706759135] slot 0 - loaded image
[1706759135] slot 0 - loaded image
[1706759135] slot 0 - loaded image
[1706759135] slot 0 is processing [task id: 0]
[1706759135] slot 0 : kv cache rm - [0, end)
[1706759135] slot 0 - encoding image [id: 0]
[1706759135] slot 0 - encoding image [id: 1]
[1706759136] slot 0 - encoding image [id: 2]
[1706759136] slot 0 - encoding image [id: 3]
[1706759136] slot 0 - encoding image [id: 4]
[1706759144] ingest_images : failed to eval image
[1706759144] failed processing images
[1706759144] unexpected error in llama server update_slots - exiting main loop
[1706759144] 
llama server shutting down

This seems to be because llama_decode returns an error due to an insufficient context window after decoding the model

Originally created by @jmorganca on GitHub (Feb 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2303 If submitting too many images via the `images` API parameter in `/api/generate` or` /api/chat` ``` [1706759134] slot 0 - loaded image [1706759135] slot 0 - loaded image [1706759135] slot 0 - loaded image [1706759135] slot 0 - loaded image [1706759135] slot 0 - loaded image [1706759135] slot 0 is processing [task id: 0] [1706759135] slot 0 : kv cache rm - [0, end) [1706759135] slot 0 - encoding image [id: 0] [1706759135] slot 0 - encoding image [id: 1] [1706759136] slot 0 - encoding image [id: 2] [1706759136] slot 0 - encoding image [id: 3] [1706759136] slot 0 - encoding image [id: 4] [1706759144] ingest_images : failed to eval image [1706759144] failed processing images [1706759144] unexpected error in llama server update_slots - exiting main loop [1706759144] llama server shutting down ``` This seems to be because `llama_decode` returns an error due to an insufficient context window after decoding the model
GiteaMirror added the bug label 2026-04-28 05:28:02 -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#47840
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?