Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature Request: update Windows actions builder to use *LATEST* Vulkan SDK (1.4.304 SDK) for VK_NV_cooperative_matrix2 support (like Linux builds).... #12294

Closed
4 tasks done
oscarbg opened this issue Mar 10, 2025 · 4 comments · Fixed by #12301
Labels
enhancement New feature or request

Comments

@oscarbg
Copy link
Contributor

oscarbg commented Mar 10, 2025

Prerequisites

  • I am running the latest code. Mention the version if possible as well.
  • I carefully followed the README.md.
  • I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

Hi,
dowloading latest Vulkan Linux build:
https://github.com/ggml-org/llama.cpp/releases/download/b4856/llama-b4856-bin-ubuntu-vulkan-x64.zip
doesn't support use of VK_NV_cooperative_matrix2..
I'm on NV VK dev driver supporting that extension.. (575 release will have that also)

./llama-bench

shows:

ggml_vulkan: 0 = NVIDIA GeForce RTX 4070 (NVIDIA) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 49152 | matrix cores: KHR_coopmat

so no VK_NV_cooperative_matrix2 support..

but on Windows:

ggml_vulkan: 0 = NVIDIA GeForce RTX 4070 (NVIDIA) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 49152 | matrix cores: NV_coopmat2

so is enabled..

Motivation

improves performance vs KHR_coopmat implementation..

Possible Implementation

it's all due to script:
https://github.com/ggml-org/llama.cpp/blob/master/.github/workflows/build.yml

on linux using latest SDK available 1.4.304 with support for that but Windows builder uses 1.3.261.1 SDK without support ..
so the fix is change in:

https://github.com/ggml-org/llama.cpp/blob/master/.github/workflows/build.yml
from:
VULKAN_VERSION: 1.3.261.1
to:
VULKAN_VERSION: 1.4.304.1

located:

 windows-latest-cmake:
    runs-on: windows-latest
..
    env:
      VULKAN_VERSION: 1.3.261.1
@oscarbg oscarbg added the enhancement New feature or request label Mar 10, 2025
@0cc4m
Copy link
Collaborator

0cc4m commented Mar 10, 2025

Has a non-beta Nvidia driver supporting VK_NV_cooperative_matrix2 been released yet? I don't think doing is worth it until you don't need a beta driver anymore.

@oscarbg
Copy link
Contributor Author

oscarbg commented Mar 10, 2025

not yet.. Ok.. but current Linux builds use that same Vulkan SDK version I'm requesting here, and have enabled VK_NV_cooperative_matrix2 already..
in any case will update here once R575 drivers released..

@0cc4m
Copy link
Collaborator

0cc4m commented Mar 10, 2025

If you want to update it beforehand, I don't mind. I wasn't aware the Linux build already has it already.

@oscarbg
Copy link
Contributor Author

oscarbg commented Mar 10, 2025

nice.. thanks.. created #12301 !

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants