Some cleanup #291
Closed
Some cleanup #291
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
…k except GFLOPS calculation
Mps matrix multiplication kernel
Improve gemm benchmark Co-authored-by: Nicolas Patry <[email protected]>
…arately of encoding.
…ments Use MatrixBuffers for encode_gemm. Do not create result buffer within.
Mpsdatatype should be u32
tl;dr. No idea why we need this, but if we don't the main thread will attempt to release the `MatrixDescriptor` and fail. This fix is a dirty hack which simply leaks those `MatrixDescriptor`. Which *seems* ok since they get cleaned up by the releasepool at the end of the program, but this is definitely a temporary workaround, which should at least enable adding a few tests on the test suite.
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Outdated suggestions cannot be applied.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.
Just some code management (disantangling pure MPS/raytracing/matrix).
Adding a demo example for compiling the custom kernels of ggml. (Still missing the preprocessor)
Feel free to reject or comment on the overall architecture change (depending on the conversaiton I might tackle some assert -> Result thing too.