mlx
mlx copied to clipboard
ml-explore
MLX: An array framework for Apple silicon
In the current implementation of Rope, we are not caching the costheta and sintheta. Instead, we compute the theta on-the-fly for every forward pass. It would be better if we...
GGUF support
## Proposed changes This adds [GGUF](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md) support using the excellent [gguflib](https://github.com/antirez/gguf-tools/blob/main/gguflib.h) from @antirez. Would there be interest in this? GGUF is currently very popular for local inference, and there are...
In my project I need to use complex-valued data. While many operations in `mlx.core` support complex arrays, there are a few basic examples missing. For example, both: ``` import mlx.core...
## Proposed changes Enables multi output primitives. Also added `divmod` as a multi-output primitive. Not so much because we need it, but I wanted to test the multi-output functionality. ####...
## Proposed changes Added initial implementation of the following learning-rate schedulers (https://github.com/ml-explore/mlx/issues/333): - StepLR - ExponentialLR - MultiStepLR - LambdaLR - PolynomialLR - CosineAnnealingLR - SequentialLR They have been adapted...
## Proposed changes Adds support for python mlx.array create from list of mlx.array's. Trying to tackle [issue 287](https://github.com/ml-explore/mlx/issues/287). ## Checklist Put an `x` in the boxes that apply. - [x]...
Add pickle support to [array](https://github.com/ml-explore/mlx/blob/main/python/src/array.cpp) through pybind, docs can be viewed [here](https://pybind11.readthedocs.io/en/latest/advanced/classes.html#pickling-support). This is a pre-req for #300
We check `contiguous` in our saving but that doesn't mean row or col contiguous. This is an issue with safetensors as well. I think it would be nice to support...
I am the maintainer of [`pyhpc-benchmarks`](https://github.com/dionhaefner/pyhpc-benchmarks), a repository that compares the performance of various JIT compilers and ML frameworks on scientific computing workloads (mostly finite difference stencils from an ocean...
Seems like all methods return arrays of same length. Need to be able to filter and return an array with less elements than what went in. Whats the best way...
