mirror of
https://github.com/ml-explore/mlx.git
synced 2025-12-16 01:49:05 +08:00
c4230747a1
* redesign for faster cpu/gpu synch * load + more async CPU * use command encoder API and move more ops to use it * make fence back-end generic + CPU only fence * faster build * fix async eval * fixes + handle temporaries * fix / improve cpu conv * remove unused status, fix siblings * fix extensions * fix * fix no cpu build * format * comments * fix perf regression, remove unecessary abort * fix events, task limit cpu * fix waiting * fix donation / temporaries in normalization
27 lines
461 B
C++
27 lines
461 B
C++
// Copyright © 2025 Apple Inc.
|
|
|
|
#pragma once
|
|
#include "mlx/array.h"
|
|
|
|
namespace mlx::core {
|
|
|
|
template <typename T>
|
|
void matmul(
|
|
const T* a,
|
|
const T* b,
|
|
T* out,
|
|
bool a_transposed,
|
|
bool b_transposed,
|
|
size_t lda,
|
|
size_t ldb,
|
|
size_t ldc,
|
|
float alpha,
|
|
float beta,
|
|
size_t batch_size,
|
|
const Shape& a_shape,
|
|
const Strides& a_strides,
|
|
const Shape& b_shape,
|
|
const Strides& b_strides);
|
|
|
|
} // namespace mlx::core
|