Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1760] [BUG]: When trying to stop the model the CPU job doesn't go down #1148

New Issue
Closed
opened 2026-02-22 18:23:22 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:23:22 -05:00
Owner
Copy Link
Copy Source

Originally created by @doggi87 on GitHub (Jun 25, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1760

How are you running AnythingLLM?

Docker (local)

What happened?

When I write something to a model and then trying to stop, it works sometimes and sometimes the CPU is still 100% even after stopping, seems that the process hangs and I need to kill the process.

Can inform that I use docker container.
I use Ryzen 7 5800h 16GB ram

Are there known steps to reproduce?

Type anything to any model like llama3 or mistral.
Let the model write and then stop in the middle and write again and stop. Sometimes the process doesn't go idle and pushing the CPU 100% even after everything is stopped.

Originally created by @doggi87 on GitHub (Jun 25, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1760 ### How are you running AnythingLLM? Docker (local) ### What happened? When I write something to a model and then trying to stop, it works sometimes and sometimes the CPU is still 100% even after stopping, seems that the process hangs and I need to kill the process. Can inform that I use docker container. I use Ryzen 7 5800h 16GB ram ### Are there known steps to reproduce? Type anything to any model like llama3 or mistral. Let the model write and then stop in the middle and write again and stop. Sometimes the process doesn't go idle and pushing the CPU 100% even after everything is stopped.
yindo added the possible bug label 2026-02-22 18:23:22 -05:00
yindo closed this issue 2026-02-22 18:23:22 -05:00
yindo commented 2026-02-22 18:23:22 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 25, 2024):

There is no detail on what LLM provider you are using here, so hard to help debug. Most LLM providers dont even support a halt method so once they start inferencing they cannot stop - all we can do client side is disconnect from the listener and hope the provider can see CONN_CLOSED and stop.

Again, most dont support this.

@timothycarambat commented on GitHub (Jun 25, 2024): There is no detail on what LLM provider you are using here, so hard to help debug. Most LLM providers dont even support a `halt` method so once they start inferencing they cannot stop - all we can do client side is disconnect from the listener and hope the provider can see `CONN_CLOSED` and stop. Again, most dont support this.
yindo commented 2026-02-22 18:23:22 -05:00
Author
Owner
Copy Link
Copy Source

@doggi87 commented on GitHub (Jun 25, 2024):

Oh okay, im using ollama api. But if ollama is the problem then they should
fix i hope.

Regards

Den tis 25 juni 2024 22:33Timothy Carambat @.***> skrev:

There is no detail on what LLM provider you are using here, so hard to
help debug. Most LLM providers dont even support a halt method so once
they start inferencing they cannot stop - all we can do client side is
disconnect from the listener and hope the provider can see CONN_CLOSED
and stop.

Again, most dont support this.

—
Reply to this email directly, view it on GitHub
https://github.com/Mintplex-Labs/anything-llm/issues/1760#issuecomment-2189917849,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AW4TPNABUZY5O5W5HYLNPXLZJHHZZAVCNFSM6AAAAABJ4QDF3GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOBZHEYTOOBUHE
.
You are receiving this because you authored the thread.Message ID:
@.***>

@doggi87 commented on GitHub (Jun 25, 2024): Oh okay, im using ollama api. But if ollama is the problem then they should fix i hope. Regards Den tis 25 juni 2024 22:33Timothy Carambat ***@***.***> skrev: > There is no detail on what LLM provider you are using here, so hard to > help debug. Most LLM providers dont even support a halt method so once > they start inferencing they cannot stop - all we can do client side is > disconnect from the listener and hope the provider can see CONN_CLOSED > and stop. > > Again, most dont support this. > > — > Reply to this email directly, view it on GitHub > <https://github.com/Mintplex-Labs/anything-llm/issues/1760#issuecomment-2189917849>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AW4TPNABUZY5O5W5HYLNPXLZJHHZZAVCNFSM6AAAAABJ4QDF3GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOBZHEYTOOBUHE> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> >
yindo commented 2026-02-22 18:23:22 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 25, 2024):

Yeah :/ I agree, believe me I have had this same issue myself and I have found just killing the process and rebooting worked when it was on a runaway inference

@timothycarambat commented on GitHub (Jun 25, 2024): Yeah :/ I agree, believe me I have had this same issue myself and I have found just killing the process and rebooting worked when it was on a runaway inference
yindo commented 2026-02-22 18:23:22 -05:00
Author
Owner
Copy Link
Copy Source

@doggi87 commented on GitHub (Jun 26, 2024):

But strange part is I tried open webui and there it works when stopping but
the performance of answer from the model is slower than anythingllm.

Den tis 25 juni 2024 22:43Timothy Carambat @.***> skrev:

Yeah :/ I agree, believe me I have had this same issue myself and I have
found just killing the process and rebooting worked when it was on a
runaway inference

—
Reply to this email directly, view it on GitHub
https://github.com/Mintplex-Labs/anything-llm/issues/1760#issuecomment-2189934834,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AW4TPNBDPKDRJEOKIDHYENTZJHJA7AVCNFSM6AAAAABJ4QDF3GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOBZHEZTIOBTGQ
.
You are receiving this because you authored the thread.Message ID:
@.***>

@doggi87 commented on GitHub (Jun 26, 2024): But strange part is I tried open webui and there it works when stopping but the performance of answer from the model is slower than anythingllm. Den tis 25 juni 2024 22:43Timothy Carambat ***@***.***> skrev: > Yeah :/ I agree, believe me I have had this same issue myself and I have > found just killing the process and rebooting worked when it was on a > runaway inference > > — > Reply to this email directly, view it on GitHub > <https://github.com/Mintplex-Labs/anything-llm/issues/1760#issuecomment-2189934834>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AW4TPNBDPKDRJEOKIDHYENTZJHJA7AVCNFSM6AAAAABJ4QDF3GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOBZHEZTIOBTGQ> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> >
yindo changed title from [BUG]: When trying to stop the model the CPU job doesn't go down to [GH-ISSUE #1760] [BUG]: When trying to stop the model the CPU job doesn't go down 2026-06-05 14:39:13 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1148
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?