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 #4267] ollama_llama_server is still running after exiting via SIGINT #49175

New Issue
Closed
opened 2026-04-28 10:53:56 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 10:53:56 -05:00
Owner
Copy Link

Originally created by @robbycbennett on GitHub (May 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4267

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When I kill ollama serve with control-C with the keyboard, it closes ollama_llama_server and therefore it all exits properly. However, when I kill it in another way like kill -2 then ollama_llama_server still runs afterward.

Replicate:

  1. OLLAMA_HOST=localhost:6767 ollama serve &
  2. Note the process ID
  3. ollama pull llama3 if you don't already have this model
  4. Post a chat
    • Run the curl command below OR
    • Run the python script included below
  5. kill -2 PROCESS_ID_HERE (2 is SIGINT, just like control-C)
# curl command to post a chat
curl http://localhost:6767/api/chat -d '{
  "model": "llama3",
  "messages": [
    {
      "role": "user",
      "content": "why is the sky blue?"
    }
  ]
}'

#! /usr/bin/env python3


# python script to post a chat


from llama_index.core import Document, Settings, VectorStoreIndex
from llama_index.embeddings.ollama import OllamaEmbedding
from llama_index.llms.ollama import Ollama


MODEL = 'llama3'
TEMPERATURE = 0.2
PORT = 6767
PROMPT = 'What is your favorite color out of the colors listed?'


def createLLM():
    llm = Ollama(
        base_url=f'http://localhost:{PORT}',
        model=MODEL,
        temperature=TEMPERATURE,
        request_timeout=60.0, # seconds
    )
    Settings.llm = llm
    Settings.embed_model = OllamaEmbedding(model_name=MODEL)


def main():
    createLLM()

    index = VectorStoreIndex.from_documents([Document(id_='colors', text='red, yellow, blue')])
    query_engine = index.as_query_engine(streaming=True)

    print(PROMPT)
    response = str(query_engine.query(PROMPT))
    print(response)


if __name__ == '__main__':
    main()

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.1.34

Originally created by @robbycbennett on GitHub (May 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4267 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When I kill `ollama serve` with control-C with the keyboard, it closes `ollama_llama_server` and therefore it all exits properly. However, when I kill it in another way like `kill -2` then `ollama_llama_server` still runs afterward. Replicate: 1. `OLLAMA_HOST=localhost:6767 ollama serve &` 2. Note the process ID 3. `ollama pull llama3` if you don't already have this model 4. Post a chat - Run the curl command below OR - Run the python script included below 5. `kill -2 PROCESS_ID_HERE` (2 is SIGINT, just like control-C) ```sh # curl command to post a chat curl http://localhost:6767/api/chat -d '{ "model": "llama3", "messages": [ { "role": "user", "content": "why is the sky blue?" } ] }' ``` ```py #! /usr/bin/env python3 # python script to post a chat from llama_index.core import Document, Settings, VectorStoreIndex from llama_index.embeddings.ollama import OllamaEmbedding from llama_index.llms.ollama import Ollama MODEL = 'llama3' TEMPERATURE = 0.2 PORT = 6767 PROMPT = 'What is your favorite color out of the colors listed?' def createLLM(): llm = Ollama( base_url=f'http://localhost:{PORT}', model=MODEL, temperature=TEMPERATURE, request_timeout=60.0, # seconds ) Settings.llm = llm Settings.embed_model = OllamaEmbedding(model_name=MODEL) def main(): createLLM() index = VectorStoreIndex.from_documents([Document(id_='colors', text='red, yellow, blue')]) query_engine = index.as_query_engine(streaming=True) print(PROMPT) response = str(query_engine.query(PROMPT)) print(response) if __name__ == '__main__': main() ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.34
GiteaMirror added the bug label 2026-04-28 10:53:56 -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#49175
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?