mirror of
https://github.com/ml-explore/mlx.git
synced 2025-12-16 01:49:05 +08:00
ec72b44417
* Add quantize/dequantize slow path for mxfp8 and nvfp4 * fast cuda kernel for mx/nv quantization * fallback for cuda < 12.8 (#2697) * format (#2700) * fix (#2701) * metal kernels * docs * fix jit * add default bits and group sizes * improve quant docs * fix output type of mxfp4 matmuls
47 lines
1.0 KiB
C++
47 lines
1.0 KiB
C++
// Copyright © 2023-2024 Apple Inc.
|
|
|
|
#pragma once
|
|
|
|
namespace mlx::core::metal {
|
|
|
|
const char* utils();
|
|
const char* binary_ops();
|
|
const char* unary_ops();
|
|
const char* ternary_ops();
|
|
const char* reduce_utils();
|
|
const char* gather();
|
|
const char* scatter();
|
|
|
|
const char* arange();
|
|
const char* unary();
|
|
const char* binary();
|
|
const char* binary_two();
|
|
const char* copy();
|
|
const char* fft();
|
|
const char* gather_axis();
|
|
const char* gather_front();
|
|
const char* hadamard();
|
|
const char* logsumexp();
|
|
const char* quantized_utils();
|
|
const char* quantized();
|
|
const char* fp_quantized();
|
|
const char* ternary();
|
|
const char* scan();
|
|
const char* scatter_axis();
|
|
const char* softmax();
|
|
const char* sort();
|
|
const char* reduce();
|
|
|
|
const char* gemm();
|
|
const char* steel_gemm_fused();
|
|
const char* steel_gemm_masked();
|
|
const char* steel_gemm_splitk();
|
|
const char* steel_gemm_gather();
|
|
const char* steel_gemm_segmented();
|
|
const char* conv();
|
|
const char* steel_conv();
|
|
const char* steel_conv_general();
|
|
const char* gemv_masked();
|
|
|
|
} // namespace mlx::core::metal
|