David Koski

Let's try this as a fix for #59 and maybe #57

**Describe the bug** broadcast of scalar array in last dimension fails after #1035 **To Reproduce** Include code snippet ```python >>> import mlx.core as mx >>> a = mx.zeros([2, 3, 4,...

missing functions from ops.h

1

I noticed that these are missing from ops.h: ``` /** * Extract the number of elements along some axes as a scalar array. Used to * allow shape dependent shapeless...

add quantized embedding

3

Part of the fix for https://github.com/ml-explore/mlx-swift-examples/issues/53 Ready!

handle partially quantized models

3

- fix for #53 #71 #69 #74 - in order to test the models - I added a default prompt of an appropriate form - while working on the model...

**Describe the bug** `mlx-swift` needs to have the various preambles (e.g. jit directory with metal shaders) built and checked in to the repository. Currently cmake picks up the SDK that...

remove gguf from mlx-swift build

2

See https://github.com/ml-explore/mlx-swift/issues/110 From @awni > Hmm, we should build without GGUF support in MLX Swift / MLX C (MLX_BUILD_GGUF=OFF). We don't support it in the API anyway so it doesn't...

Make mlx-vlm examples in swift

2

Consider porting some models from https://github.com/Blaizzy/mlx-vlm to swift

- based on #125 with simpler mechanism (NSLock)

Adopt new API from https://github.com/ml-explore/mlx-c/pull/38