|
array | mlx::core::fast::rms_norm (const array &x, const array &weight, float eps, StreamOrDevice s={}) |
|
array | mlx::core::fast::layer_norm (const array &x, const std::optional< array > &weight, const std::optional< array > &bias, float eps, StreamOrDevice s={}) |
|
array | mlx::core::fast::rope (const array &x, int dims, bool traditional, std::optional< float > base, float scale, int offset, const std::optional< array > &freqs=std::nullopt, StreamOrDevice s={}) |
|
array | mlx::core::fast::scaled_dot_product_attention (const array &queries, const array &keys, const array &values, const float scale, const std::optional< array > &mask=std::nullopt, const std::optional< int > memory_efficient_threshold=std::nullopt, StreamOrDevice s={}) |
| Computes: O = softmax(Q @ K.T) @ V.
|
|
std::tuple< array, array, array > | mlx::core::fast::affine_quantize (const array &w, int group_size=64, int bits=4, StreamOrDevice s={}) |
|
array | mlx::core::fast::affine_quantize (const array &w, const array &scales, const array &biases, int group_size=64, int bits=4, StreamOrDevice s={}) |
|
array | mlx::core::fast::affine_dequantize (const array &w, const array &scales, const array &biases, int group_size=64, int bits=4, StreamOrDevice s={}) |
|
MetalKernelFunction | mlx::core::fast::metal_kernel (const std::string &name, const std::vector< std::string > &input_names, const std::vector< std::string > &output_names, const std::string &source, const std::string &header="", bool ensure_row_contiguous=true, bool atomic_outputs=false) |
|