Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #2249] [BUG]: #1469

New Issue
Closed
opened 2026-02-22 18:24:58 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:24:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @soturiBerg on GitHub (Sep 9, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2249

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Good afternoon! Just started with a fresh install of AnythingLLM, downloaded and activated the Llama3.1 8B model and tried to prompt it but keep receiving the following error: "llama runner process has terminated: CUDA error".

I have not been able to find any posts on the web regarding the exact same error. Is there anything I can do to fix this? Note: I have been able to get this model to work in a different tool called GPT4all, so it should work.

extra device info:

Windows 10, using latest installation version of AnythingLLM
GPU = AMD 6650XT

Screenshot (556)

Are there known steps to reproduce?

No response

Originally created by @soturiBerg on GitHub (Sep 9, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2249 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? Good afternoon! Just started with a fresh install of AnythingLLM, downloaded and activated the Llama3.1 8B model and tried to prompt it but keep receiving the following error: "llama runner process has terminated: CUDA error". I have not been able to find any posts on the web regarding the exact same error. Is there anything I can do to fix this? Note: I have been able to get this model to work in a different tool called GPT4all, so it should work. extra device info: Windows 10, using latest installation version of AnythingLLM GPU = AMD 6650XT ![Screenshot (556)](https://github.com/user-attachments/assets/cadf4375-640e-4438-80ab-1d80e711e1bd) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:24:58 -05:00
yindo closed this issue 2026-02-22 18:24:58 -05:00
yindo commented 2026-02-22 18:24:58 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Sep 9, 2024):

GPU = AMD 6650XT

We dont currently ship the ROCM bindings for AMD cards (>1GB) so instead of trying to patch this in the app, which will be frustrating you can install Ollama and connect to that as an external LLM.

Not ideal, we know about this bug though and it is tracked elsewhere and will be patched soon

@timothycarambat commented on GitHub (Sep 9, 2024): > GPU = AMD 6650XT We dont currently ship the ROCM bindings for AMD cards (>1GB) so instead of trying to patch this in the app, which will be frustrating you can install [Ollama](https://ollama.com) and connect to _that_ as an external LLM. Not ideal, we know about this bug though and it is tracked elsewhere and will be patched soon
yindo commented 2026-02-22 18:24:58 -05:00
Author
Owner
Copy Link
Copy Source

@ojsl1 commented on GitHub (Apr 30, 2025):

We dont currently ship the ROCM bindings for AMD cards (>1GB) so instead of trying to patch this in the app, which will be frustrating you can install Ollama and connect to that as an external LLM.

Not ideal, we know about this bug though and it is tracked elsewhere and will be patched soon

Where exactly is it tracked currently, and is it implemented yet (after a year)?

@ojsl1 commented on GitHub (Apr 30, 2025): > > We dont currently ship the ROCM bindings for AMD cards (>1GB) so instead of trying to patch this in the app, which will be frustrating you can install [Ollama](https://ollama.com) and connect to _that_ as an external LLM. > > Not ideal, we know about this bug though and it is tracked elsewhere and will be patched soon Where exactly is it tracked currently, and is it implemented yet (after a year)?
yindo commented 2026-02-22 18:24:58 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 30, 2025):

It has been live for almost a year now. Since like 1.2.x IIRC

@timothycarambat commented on GitHub (Apr 30, 2025): It has been live for almost a year now. Since like 1.2.x IIRC
yindo changed title from [BUG]: to [GH-ISSUE #2249] [BUG]: 2026-06-05 14:40:55 -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#1469
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?