Better GPU backend detection + flake variants#244
Open
Better GPU backend detection + flake variants#244
Conversation
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In the original version - if CUDA libraries are installed the code will never try Metal or Vulkan as a fallback. This refactors the GPU backend selection to only try supported backends and to try all in order during fallbacks.
I also updated flake.nix and added a variant for Vulkan - because my system doesn't support CUDA. (I haven't tested the other variants - but flake.nix was broken to begin with...)
(I had to bump node-llama-cpp to 3.16 to fix a Vulkan header issue in llama/gpuInfo/vulkan-gpu-info.cpp fixed by withcatai/node-llama-cpp@57e8c22.)
Testing
bun src/qmd.ts statusbun src/qmd.ts embedbun src/qmd.ts query