github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-11 04:33:12 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7663] Ollama API Multiple thread error reporting, abnormal thread time consumption #4890

New Issue
Closed
opened 2026-04-12 15:55:41 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:55:41 -05:00
Owner
Copy Link

Originally created by @jamine2024 on GitHub (Nov 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7663

What is the issue?

Error：
msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-13T20:41:50.757+08:00 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled"

USE PYTHON API Find some error with server.log

`url = f'{ollama_api}/api/generate'
headers = {'Content-Type': 'application/json'}
data = {
"model": ollama_mode,
"prompt": f'{title} {config.get("out", "content")}'
}

response = requests.post(url, headers=headers, json=data, timeout=120)
responses = ''.join(json.loads(line)["response"] for line in response.text.split('\n') if line)`

How to deal with multithreading will lead to the API response delay, and eventually will appear as raised at the beginning!
Is there a scheme to end the thread?
1731562882316

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.4.1

Originally created by @jamine2024 on GitHub (Nov 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7663 ### What is the issue? Error： msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-13T20:41:50.757+08:00 level=ERROR source=server.go:690 msg="Failed to acquire semaphore" error="context canceled" USE PYTHON API Find some error with server.log `url = f'{ollama_api}/api/generate' headers = {'Content-Type': 'application/json'} data = { "model": ollama_mode, "prompt": f'{title} {config.get("out", "content")}' } response = requests.post(url, headers=headers, json=data, timeout=120) responses = ''.join(json.loads(line)["response"] for line in response.text.split('\n') if line)` How to deal with multithreading will lead to the API response delay, and eventually will appear as raised at the beginning! Is there a scheme to end the thread? ![1731562882316](https://github.com/user-attachments/assets/514648d0-6c40-404d-b836-59677ac1ed3b) ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.1
GiteaMirror added the bug label 2026-04-12 15:55:41 -05:00
GiteaMirror commented 2026-04-12 15:55:43 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 14, 2024):

This looks like it is the same as #7545 so let's track it there. However, this may already be fixed - if you are able to build from main to test it that would be very helpful.

<!-- gh-comment-id:2477118425 --> @jessegross commented on GitHub (Nov 14, 2024): This looks like it is the same as #7545 so let's track it there. However, this may already be fixed - if you are able to build from `main` to test it that would be very helpful.
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#4890
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?