Add GGML_VK_VISIBLE_DEVICES env var

[ericcurtin]

Can be used to manually select vulkan device

Summary by Sourcery

Add support for the GGML_VK_VISIBLE_DEVICES environment variable to enable manual Vulkan device selection and update related configuration and documentation.

New Features:

• Introduce the GGML_VK_VISIBLE_DEVICES env var for manual Vulkan GPU selection.

Enhancements:

• Include GGML_VK_VISIBLE_DEVICES in the GPU environment variable list and config mappings.

Documentation:

• Update the README accelerator table to reference GGML_VK_VISIBLE_DEVICES as the Vulkan/CPU selector.

[sourcery-ai]

Reviewer's Guide

Introduces the GGML_VK_VISIBLE_DEVICES environment variable to enable manual Vulkan device selection, updates documentation, and integrates the new variable into runtime detection and configuration.

Class diagram for updated BaseConfig environment variable mapping

classDiagram
    class BaseConfig {
        +dict env_var_to_image
    }
    BaseConfig : env_var_to_image["GGML_VK_VISIBLE_DEVICES"] = "quay.io/ramalama/ramalama"

Loading

File-Level Changes

Change	Details	Files
Updated documentation to include GGML_VK_VISIBLE_DEVICES in the accelerator table	Reformatted table header for consistent column widths Replaced the "CPU, Vulkan, Apple" entry with "GGML_VK_VISIBLE_DEVICES (or CPU)"	README.md
Registered the new env var in GPU detection logic	Added "GGML_VK_VISIBLE_DEVICES" to the list in set_gpu_type_env_vars	ramalama/common.py
Mapped GGML_VK_VISIBLE_DEVICES to the default container image	Inserted "GGML_VK_VISIBLE_DEVICES": "quay.io/ramalama/ramalama" into the BaseConfig model images	ramalama/config.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[gemini-code-assist]

Summary of Changes

Hello @ericcurtin, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the system's flexibility by introducing a dedicated environment variable, GGML_VK_VISIBLE_DEVICES, for explicit Vulkan device selection. This change provides users with more granular control over GPU utilization, and it includes the necessary updates to both documentation and internal configuration to fully support this new functionality.

Highlights

• New Environment Variable: Introduced GGML_VK_VISIBLE_DEVICES as a new environment variable, allowing users to manually select a specific Vulkan device for acceleration.
• Documentation Update: Updated the README.md file to reflect the new GGML_VK_VISIBLE_DEVICES environment variable in the 'Accelerated images' table, clarifying its use for Vulkan acceleration.
• System Integration: Integrated the new environment variable into the system's configuration (ramalama/common.py and ramalama/config.py) to ensure it is recognized and correctly maps to the quay.io/ramalama/ramalama container image, which provides Vulkan support.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces the GGML_VK_VISIBLE_DEVICES environment variable for manual Vulkan device selection, updates related configurations, and updates the README. The changes look good overall, with minor suggestions for improved clarity and maintainability.

[sourcery-ai]

Hey @ericcurtin - I've reviewed your changes - here's some feedback:

• The detection order in set_gpu_type_env_vars places GGML_VK_VISIBLE_DEVICES after CUDA, but your README table lists it first—please reconcile the priority order between code and documentation.
• Consider adding a quick usage example in the README showing how to set GGML_VK_VISIBLE_DEVICES to explicitly select a Vulkan device.

Prompt for AI Agents

Please address the comments from this code review:
## Overall Comments
- The detection order in `set_gpu_type_env_vars` places GGML_VK_VISIBLE_DEVICES after CUDA, but your README table lists it first—please reconcile the priority order between code and documentation.
- Consider adding a quick usage example in the README showing how to set GGML_VK_VISIBLE_DEVICES to explicitly select a Vulkan device.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[rhatdan]

Would it be simpler to just name this VULKAN_VISIBLE_DEVICES?

[ericcurtin]

It wouldn't because these env var names are all from llama.cpp

[rhatdan]

LGTM