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

11
ggml/src/ggml-cpu/ggml-cpu.c
View File

@@ -1193,7 +1193,7 @@ static void ggml_compute_forward_mul_mat_one_chunk(
}
}
static void ggml_compute_forward_mul_mat(
void ggml_compute_forward_mul_mat(
const struct ggml_compute_params * params,
struct ggml_tensor * dst) {
@@ -1866,6 +1866,10 @@ static void ggml_compute_forward(struct ggml_compute_params * params, struct ggm
{
ggml_compute_forward_im2col_back_f32(params, tensor);
} break;
case GGML_OP_CONV_2D:
{
ggml_compute_forward_conv_2d(params, tensor);
} break;
case GGML_OP_CONV_2D_DW:
{
ggml_compute_forward_conv_2d_dw(params, tensor);
@@ -2228,6 +2232,7 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) {
} break;
case GGML_OP_IM2COL:
case GGML_OP_IM2COL_BACK:
case GGML_OP_CONV_2D:
case GGML_OP_CONV_2D_DW:
case GGML_OP_CONV_TRANSPOSE_1D:
case GGML_OP_CONV_TRANSPOSE_2D:
@@ -2746,6 +2751,10 @@ struct ggml_cplan ggml_graph_plan(
GGML_ABORT("fatal error");
}
} break;
case GGML_OP_CONV_2D:
{
cur = GGML_IM2COL_WORK_SIZE;
} break;
case GGML_OP_CONV_TRANSPOSE_2D:
{
const int64_t ne00 = node->src[0]->ne[0]; // W