github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1397] No concurrent query. Error: unexpected end of response #62777

New Issue
Closed
opened 2026-05-03 10:17:42 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 10:17:42 -05:00
Owner
Copy Link

Originally created by @fxrobin on GitHub (Dec 6, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1397

Trying to simultaneously quering Ollama results in a failure :

The first query is "served" but the second is ignore.

First request :

image

Second request in parallel :

image

Is it a limitation of Ollama ?

Originally created by @fxrobin on GitHub (Dec 6, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1397 Trying to simultaneously quering Ollama results in a failure : The first query is "served" but the second is ignore. First request : ![image](https://github.com/jmorganca/ollama/assets/16342334/70140b70-84ba-42d0-8755-79684a506ac3) Second request in parallel : ![image](https://github.com/jmorganca/ollama/assets/16342334/600b1753-9912-4bbd-b9dc-84d390d3f143) Is it a limitation of Ollama ?
GiteaMirror commented 2026-05-03 10:17:44 -05:00
Author
Owner
Copy Link

@contextcompanion commented on GitHub (Dec 6, 2023):

I'm working on an app which makes parallel requests. As of the latest version (0.1.13) I am seeing this issue as well. Prior to this version (though I don't know exactly which version I was using before this), issuing parallel requests would eventually yield a result for all outstanding requests (even if the processing was handled serially internally by the ollama service). This appears to be a regression in a recent version.

<!-- gh-comment-id:1843862043 --> @contextcompanion commented on GitHub (Dec 6, 2023): I'm working on an app which makes parallel requests. As of the latest version (0.1.13) I am seeing this issue as well. Prior to this version (though I don't know exactly which version I was using before this), issuing parallel requests would eventually yield a result for all outstanding requests (even if the processing was handled serially internally by the ollama service). This appears to be a regression in a recent version.
GiteaMirror commented 2026-05-03 10:17:44 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 9, 2023):

should be fixed with #1445

<!-- gh-comment-id:1848781420 --> @pdevine commented on GitHub (Dec 9, 2023): should be fixed with #1445
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
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#62777
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?