CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Conv2d for CPU (#14388)

Browse Source 
* Conv2D: Add CPU version

* Half decent

* Tiled approach for F32

* remove file

* Fix tests

* Support F16 operations

* add assert about size

* Review: further formatting fixes, add assert and use CPU version of fp32->fp16
This commit is contained in:
Aman Gupta
2025-06-30 23:57:04 +08:00
committed by GitHub
parent 745f11fed0
commit 0a5a3b5cdf
5 changed files with 250 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
ggml/src/ggml.c
View File

@@ -945,6 +945,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
"CONV_TRANSPOSE_1D",
"IM2COL",
"IM2COL_BACK",
"CONV_2D",
"CONV_2D_DW",
"CONV_TRANSPOSE_2D",
"POOL_1D",
@@ -986,7 +987,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
"GLU",
};
static_assert(GGML_OP_COUNT == 85, "GGML_OP_COUNT != 85");
static_assert(GGML_OP_COUNT == 86, "GGML_OP_COUNT != 86");
static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
"none",
@@ -1044,6 +1045,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
"conv_transpose_1d(x)",
"im2col(x)",
"im2col_back(x)",
"conv_2d(x)",
"conv_2d_dw(x)",
"conv_transpose_2d(x)",
"pool_1d(x)",
@@ -1085,7 +1087,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
"glu(x)",
};
static_assert(GGML_OP_COUNT == 85, "GGML_OP_COUNT != 85");
static_assert(GGML_OP_COUNT == 86, "GGML_OP_COUNT != 86");
static_assert(GGML_OP_POOL_COUNT == 2, "GGML_OP_POOL_COUNT != 2");
@@ -4291,6 +4293,44 @@ struct ggml_tensor * ggml_conv_2d_dw_direct(
return result;
}
// ggml_conv_2d_direct
struct ggml_tensor * ggml_conv_2d_direct(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel [KW, KH, IC, OC]
struct ggml_tensor * b, // input data [W, H, C, N]
int s0, // stride dimension 0
int s1, // stride dimension 1
int p0, // padding dimension 0
int p1, // padding dimension 1
int d0, // dilation dimension 0
int d1) {// dilation dimension 1
GGML_ASSERT(a->ne[2] == b->ne[2]);
//GGML_ASSERT(a->type == b->type);
int64_t ne[4];
ne[0] = ggml_calc_conv_output_size(b->ne[0], a->ne[0], s0, p0, d0);
ne[1] = ggml_calc_conv_output_size(b->ne[1], a->ne[1], s1, p1, d1);
ne[2] = a->ne[3];
ne[3] = b->ne[3];
struct ggml_tensor * result = ggml_new_tensor(ctx, b->type, 4, ne);
ggml_set_op_params_i32(result, 0, s0);
ggml_set_op_params_i32(result, 1, s1);
ggml_set_op_params_i32(result, 2, p0);
ggml_set_op_params_i32(result, 3, p1);
ggml_set_op_params_i32(result, 4, d0);
ggml_set_op_params_i32(result, 5, d1);
result->op = GGML_OP_CONV_2D;
result->src[0] = a;
result->src[1] = b;
return result;
}
// ggml_conv_transpose_2d_p0
static int64_t ggml_calc_conv_transpose_output_size(int64_t ins, int64_t ks, int s, int p) {