feat: Switch vulkan images to the kompute backend #83
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jeffmaury
changed the title
jeffmaury
reviewed
Dec 5, 2024
| dnf install -y git cmake ninja-build gcc gcc-c++ vulkan-loader-devel vulkan-tools && \ | ||
| dnf install -y mesa-vulkan-drivers-24.1.2-101.el9.aarch64 && \ | ||
| dnf versionlock mesa-vulkan-drivers-24.1.2-101.el9.aarch64 && \ | ||
| dnf install -y git cmake ninja-build gcc gcc-c++ vulkan-loader-devel vulkan-tools fmt-devel && \ | ||
| dnf copr enable -y jeffmaury/shaderc epel-9-aarch64 && \ |
There was a problem hiding this comment.
This part was added recently because it was required by the llama-cpp Vulkan build, is it still required for kompute ?
There was a problem hiding this comment.
Yes, I updated the mesa package because el9 has switched to a newer llvm.
There was a problem hiding this comment.
Sorry I was not clear enough. I was mentioning the sharerc/glslc part
Signed-off-by: Sergio Lopez <[email protected]>
The latest versions of MoltenVK (tested with 1.2.11) are not able to deal properly with llama.cpp's Vulkan (GGML_VULKAN) backend. Switch our Vulkan images to use the Kompute (GGML_KOMPUTE) backend instead, which works fine with MoltenVK and will eventually achieve the same performance as Metal on macOS bare-metal. Signed-off-by: Sergio Lopez <[email protected]>
slp
force-pushed
the
switch-to-kompute
branch
3 times, most recently
from
665759f to
188866a
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The latest versions of MoltenVK (tested with 1.2.11) are not able to deal properly with llama.cpp's Vulkan (GGML_VULKAN) backend.
Switch our Vulkan images to use the Kompute (GGML_KOMPUTE) backend instead, which works fine with MoltenVK and will eventually achieve the same performance as Metal on macOS bare-metal.