open-webui/desktop

Fork 0

mirror of https://github.com/open-webui/desktop.git synced 2026-11-05 01:27:46 +00:00

[PR #214] feat: Add ROCm detection and rocm variant support #228

New issue

Open

opened 2026-10-18 14:07:09 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:07:09 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/desktop/pull/214
Author: @leonardopereira10
Created: 5/25/2026
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (1)

38c3659 Add ROCm detection and rocm variant support

📊 Changes

2 files changed (+52 additions, -13 deletions)

View changed files

📝 src/main/utils/llamacpp.ts (+50 -12)
📝 src/renderer/src/lib/components/Main/Settings/InferenceRuntime.svelte (+2 -1)

📄 Description

#208 Detect AMD/ROCm GPUs and expose a rocm variant. On Linux, detection checks for /opt/rocm or /usr/lib/rocm. On Windows, dxdiag is invoked and parsed for Adapter Family gfx identifiers (supported gfx list added) to identify AMD GPUs; temporary dxdiag_output.txt is cleaned up and protected with try/catch. Also added a Windows rocm asset name in getAssetPattern and added the 'rocm' option to the inference runtime UI.

Description

I included the autodetect implementation, but I should at least keep the option to choose ROCm as the backend, as it offers better stability in contexts with more than 20,000 tokens.

Autodetect is based on a parsing of Windows DxDiag to identify the supported GPU for ROCm (as per the list provided in the HIP documentation).

The download and extraction of HIP versions from llama.cpp has been adjusted by adding the item to the dictionary.

An option has been added to the backend configuration screen to allow selecting llama.cpp HIP/ROCm.

Closes #208

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/desktop/pull/214 **Author:** [@leonardopereira10](https://github.com/leonardopereira10) **Created:** 5/25/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`38c3659`](https://github.com/open-webui/desktop/commit/38c36594c376b1d8b5ea2084424049b833e4210e) Add ROCm detection and rocm variant support ### 📊 Changes **2 files changed** (+52 additions, -13 deletions) <details> <summary>View changed files</summary> 📝 `src/main/utils/llamacpp.ts` (+50 -12) 📝 `src/renderer/src/lib/components/Main/Settings/InferenceRuntime.svelte` (+2 -1) </details> ### 📄 Description #208 Detect AMD/ROCm GPUs and expose a rocm variant. On Linux, detection checks for /opt/rocm or /usr/lib/rocm. On Windows, dxdiag is invoked and parsed for Adapter Family gfx identifiers (supported gfx list added) to identify AMD GPUs; temporary dxdiag_output.txt is cleaned up and protected with try/catch. Also added a Windows rocm asset name in getAssetPattern and added the 'rocm' option to the inference runtime UI. ## Description  I included the autodetect implementation, but I should at least keep the option to choose ROCm as the backend, as it offers better stability in contexts with more than 20,000 tokens. Autodetect is based on a parsing of Windows DxDiag to identify the supported GPU for ROCm (as per the list provided in the HIP documentation). The download and extraction of HIP versions from llama.cpp has been adjusted by adding the item to the dictionary. An option has been added to the backend configuration screen to allow selecting llama.cpp HIP/ROCm. ## Related Issues Closes #208  --- ## Contributor License Agreement  - [x] By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/desktop/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. > [!NOTE] > Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi added the

pull-request

label

2026-10-18 14:07:09 +00:00

No labels

help wanted

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

open-webui/desktop#228

No description provided.

Rows
Columns