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 #2115] [BUG]: AMD GPU NOT (WASN'T) BEING UTILIZED for AnythingLLM for LLM Provider. #1379

New Issue
Closed
opened 2026-02-22 18:24:31 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:24:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @daveycombs on GitHub (Aug 14, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2115

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

When using AnythingLLM as the LLM Provider with my AMD 6800xt the GPU wasn't being used. With a separate Ollama instance of 0.3.6 would use my GPU I replaced the older 0.3.4 Ollama (llm.exe) files and folders in anythingllm/resources/ollama I also included the additional rocm folder from 0.3.6 which seemed to fix the issue.

I also tested Ollama 0.3.6 with and without rocm and it would not utilize the GPU without rocm included

floorp_D9TCdNZzIi

Are there known steps to reproduce?

No response

Originally created by @daveycombs on GitHub (Aug 14, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2115 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? When using AnythingLLM as the LLM Provider with my AMD 6800xt the GPU wasn't being used. With a separate Ollama instance of 0.3.6 would use my GPU I replaced the older 0.3.4 Ollama (llm.exe) files and folders in anythingllm/resources/ollama I also included the additional rocm folder from 0.3.6 which seemed to fix the issue. I also tested Ollama 0.3.6 with and without rocm and it would not utilize the GPU without rocm included ![floorp_D9TCdNZzIi](https://github.com/user-attachments/assets/cfdb7766-a0b5-473c-b52f-e55b342fcbbf) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:24:31 -05:00
yindo closed this issue 2026-02-22 18:24:32 -05:00
yindo commented 2026-02-22 18:24:32 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Aug 14, 2024):

This is already a known issue and is being track off-github since the desktop electron wrapper is not part of the OSS Repo, but yes, the reason AMD cards wont be leverage is due to ROCM not be included in Ollama - we currently prepack the llama_runners into the app but doing so will bloat the app to multiple GBs, so we will be implementing a post-install script to download the required resources so that rocm and other runners will be present

@timothycarambat commented on GitHub (Aug 14, 2024): This is already a known issue and is being track off-github since the desktop electron wrapper is not part of the OSS Repo, but yes, the reason AMD cards wont be leverage is due to ROCM not be included in Ollama - we currently prepack the llama_runners into the app but doing so will bloat the app to multiple GBs, so we will be implementing a post-install script to download the required resources so that rocm and other runners will be present
yindo changed title from [BUG]: AMD GPU NOT (WASN'T) BEING UTILIZED for AnythingLLM for LLM Provider. to [GH-ISSUE #2115] [BUG]: AMD GPU NOT (WASN'T) BEING UTILIZED for AnythingLLM for LLM Provider. 2026-06-05 14:40:26 -04:00
yindo commented 2026-06-05 14:40:27 -04:00
Author
Owner
Copy Link
Copy Source

@crnisamuraj commented on GitHub (Mar 12, 2026):

any update on this? anythingLLm desktop is still running models on CPU on linux with AMD GPU

<!-- gh-comment-id:4051856021 --> @crnisamuraj commented on GitHub (Mar 12, 2026): any update on this? anythingLLm desktop is still running models on CPU on linux with AMD GPU
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#1379
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?