mirror of
https://github.com/ollama/ollama.git
synced 2026-11-22 00:01:45 +00:00
The MLX runner is the only Go inference runner left and is no longer experimental, so its packages leave x/. The bindings become a top-level mlx package beside the carried patches in mlx/compat, mirroring how llama/ holds the llama.cpp integration, and the runner becomes mlxrunner with the architectures nested under the package they implement. Subpackages move with their parent unless listed. x/mlxrunner/mlx mlx x/internal/mlxthread mlx/mlxthread x/internal/mlxthreadtest mlx/mlxthread/mlxthreadtest x/internal/mlxtest mlx/mlxtest x/quant mlx/quant mlx/compat/*.patch mlx/compat/mlx-c (MLX patches go in mlx/compat/mlx) x/mlxrunner mlxrunner x/models/nn mlxrunner/nn x/models/<arch> mlxrunner/model/<arch> x/mlxrunner/imports.go mlxrunner/model/architectures (new package) x/create create x/safetensors fs/safetensors x/tokenizer mlxrunner/tokenizer Every package keeps its name, so the Go changes are the import path rewrites the moves force, and the CMake, Dockerfile, CI cache keys, drift check and Darwin payload script follow the new paths. Four edits are not paths: the runner's blank architecture imports become the package mlxrunner/model/architectures, so the list to extend for a new model sits beside the architecture directories; a depguard rule keeps the two test harnesses out of non-test code, as the x/internal placement used to; the CI change filter's two entries for the long-deleted x/imagegen/mlx now name the bindings' CMake project and the carried patches, so a change to either builds the payload; and the tokenizer parity test reads its fixtures from its own testdata instead of walking out of x/. x/server and x/imagegen/manifest stay for the next two commits.
68 lines
1.7 KiB
C
68 lines
1.7 KiB
C
/* Copyright © 2023-2024 Apple Inc. */
|
|
/* */
|
|
/* This file is auto-generated. Do not edit manually. */
|
|
/* */
|
|
|
|
#ifndef MLX_TRANSFORMS_H
|
|
#define MLX_TRANSFORMS_H
|
|
|
|
#include <stdbool.h>
|
|
#include <stdint.h>
|
|
#include <stdio.h>
|
|
|
|
#include "mlx/c/array.h"
|
|
#include "mlx/c/closure.h"
|
|
#include "mlx/c/distributed_group.h"
|
|
#include "mlx/c/io_types.h"
|
|
#include "mlx/c/map.h"
|
|
#include "mlx/c/stream.h"
|
|
#include "mlx/c/string.h"
|
|
#include "mlx/c/vector.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/**
|
|
* \defgroup transforms Transform operations
|
|
*/
|
|
/**@{*/
|
|
|
|
int mlx_async_eval(const mlx_vector_array outputs);
|
|
int mlx_checkpoint(mlx_closure* res, const mlx_closure fun);
|
|
int mlx_custom_function(
|
|
mlx_closure* res,
|
|
const mlx_closure fun,
|
|
const mlx_closure_custom fun_vjp /* may be null */,
|
|
const mlx_closure_custom_jvp fun_jvp /* may be null */,
|
|
const mlx_closure_custom_vmap fun_vmap /* may be null */);
|
|
int mlx_custom_vjp(
|
|
mlx_closure* res,
|
|
const mlx_closure fun,
|
|
const mlx_closure_custom fun_vjp);
|
|
int mlx_eval(const mlx_vector_array outputs);
|
|
int mlx_jvp(
|
|
mlx_vector_array* res_0,
|
|
mlx_vector_array* res_1,
|
|
const mlx_closure fun,
|
|
const mlx_vector_array primals,
|
|
const mlx_vector_array tangents);
|
|
int mlx_value_and_grad(
|
|
mlx_closure_value_and_grad* res,
|
|
const mlx_closure fun,
|
|
const int* argnums,
|
|
size_t argnums_num);
|
|
int mlx_vjp(
|
|
mlx_vector_array* res_0,
|
|
mlx_vector_array* res_1,
|
|
const mlx_closure fun,
|
|
const mlx_vector_array primals,
|
|
const mlx_vector_array cotangents);
|
|
|
|
/**@}*/
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif
|