EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

metal : refactor + optimize v2 (#15995)

Browse Source 
* metal : improve naming

* metal : refactor device

ggml-ci

* cont : props

ggml-ci

* metal : apply ggml_mem_ranges_t

ggml-ci

* metal : remove GGML_METAL_USE_BF16

ggml-ci

* metal : refactor device buffer

ggml-ci

* cont : fix naming

* metal : sync before destroying the backend

ggml-ci

* metal : refactor context

ggml-ci

* metal : migrate ggml-metal.m to ggml-metal.cpp

ggml-ci

* metal : adjust ops API

ggml-ci

* metal : use C++ to store piplienes

ggml-ci

* metal : migrate ops to separate functions

ggml-ci

* metal : add ggml_metal_library_t

ggml-ci

* metal : improve naming

ggml-ci

* metal : cleanp

ggml-ci

* metal : add support for GGML_OP_LOG

ggml-ci

* metal : fix error handling

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-09-17 20:38:12 +03:00
committed by GitHub
parent a7a98e0fff
commit 0320ac5264
19 changed files with 7873 additions and 7184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
ggml/src/ggml-metal/ggml-metal-ops.h Normal file
View File

@@ -0,0 +1,81 @@
#pragma once
#include "ggml-metal-device.h"
#ifdef __cplusplus
extern "C" {
#endif
typedef struct ggml_metal_op * ggml_metal_op_t;
ggml_metal_op_t ggml_metal_op_init(
ggml_metal_device_t dev,
ggml_metal_cmd_buf_t cmd_buf,
struct ggml_cgraph * gf,
int idx_start,
int idx_end,
bool use_fusion,
bool use_concurrency,
bool use_capture,
int debug_graph,
int debug_fusion);
void ggml_metal_op_free(ggml_metal_op_t ctx);
int ggml_metal_op_encode(ggml_metal_op_t ctx, int idx);
//
// available ops:
//
// tokens per expert
size_t ggml_metal_op_mul_mat_id_extra_tpe(const struct ggml_tensor * op);
// id map [n_tokens, n_expert]
size_t ggml_metal_op_mul_mat_id_extra_ids(const struct ggml_tensor * op);
// return true if we should use the FA vector kernel for this op
bool ggml_metal_op_flash_attn_ext_use_vec(const struct ggml_tensor * op);
size_t ggml_metal_op_flash_attn_ext_extra_tmp(const struct ggml_tensor * op);
int ggml_metal_op_concat (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_repeat (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_acc (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_scale (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_clamp (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_unary (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_glu (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_sum_rows (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_get_rows (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_set_rows (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_soft_max (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_ssm_conv (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_ssm_scan (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_rwkv (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_cpy (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_pool_2d (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_mul_mat (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_mul_mat_id (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_add_id (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_flash_attn_ext (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_bin (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_rms_norm (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_l2_norm (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_group_norm (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_norm (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_rope (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_im2col (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_conv_transpose_1d (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_upscale (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_pad (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_pad_reflect_1d (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_arange (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_timestep_embedding(ggml_metal_op_t ctx, int idx);
int ggml_metal_op_argmax (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_argsort (ggml_metal_op_t ctx, int idx);
int ggml_metal_op_leaky_relu (ggml_metal_op_t ctx, int idx);
#ifdef __cplusplus
}
#endif