diff --git a/bin/nnc/cifar-10.c b/bin/nnc/cifar-10.c
index 1d52ceaf8..2b2acb106 100644
--- a/bin/nnc/cifar-10.c
+++ b/bin/nnc/cifar-10.c
@@ -24,16 +24,16 @@ static ccv_cnnp_model_t* _building_block_new(const int filters, const int stride
 	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(identity, MODEL_IO_LIST(input));
 	if (projection_shortcut)
 	{
-		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), 1, HINT((strides, strides), (0, 0)), 0, 1, 0);
+		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((strides, strides), (0, 0)), 0, 1, 0);
 		shortcut = ccv_cnnp_model_apply(conv0, MODEL_IO_LIST(output));
 	}
 	ccv_cnnp_model_t* const conv1 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((strides, strides), (border, border)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((strides, strides), (border, border)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv1, MODEL_IO_LIST(output));
-	ccv_cnnp_model_t* const conv2 = ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0);
+	ccv_cnnp_model_t* const conv2 = ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0);
 	output = ccv_cnnp_model_apply(conv2, MODEL_IO_LIST(output));
 	ccv_cnnp_model_t* const add = ccv_cnnp_sum(0);
 	output = ccv_cnnp_model_apply(add, MODEL_IO_LIST(output, shortcut));
@@ -57,7 +57,7 @@ static ccv_cnnp_model_t* _block_layer_new(const int filters, const int strides,
 ccv_cnnp_model_t* _cifar_10_resnet56(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
-	ccv_cnnp_model_t* init_conv = ccv_cnnp_convolution(1, 16, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0);
+	ccv_cnnp_model_t* init_conv = ccv_cnnp_convolution(1, 16, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0);
 	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(init_conv, MODEL_IO_LIST(input));
 	output = ccv_cnnp_model_apply(_block_layer_new(16, 1, 1, 9), MODEL_IO_LIST(output));
 	output = ccv_cnnp_model_apply(_block_layer_new(32, 2, 1, 9), MODEL_IO_LIST(output));
@@ -78,7 +78,7 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 {
 	ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
@@ -89,13 +89,13 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 	{
 		ccv_cnnp_model_io_t shortcut = output;
 		ccv_cnnp_model_t* res1 = ccv_cnnp_sequential_new(MODEL_LIST(
-			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 			ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 			ccv_cnnp_relu(0)
 		), 1, 0);
 		output = ccv_cnnp_model_apply(res1, MODEL_IO_LIST(output));
 		ccv_cnnp_model_t* res2 = ccv_cnnp_sequential_new(MODEL_LIST(
-			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 			ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 			ccv_cnnp_relu(0)
 		), 1, 0);
@@ -109,7 +109,7 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 ccv_cnnp_model_t* _cifar_10_dawn(void)
 {
 	ccv_cnnp_model_t* prep = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
@@ -129,15 +129,15 @@ ccv_cnnp_model_t* _cifar_10_dawn(void)
 ccv_cnnp_model_t* _cifar_10_alexnet(void)
 {
 	return ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
diff --git a/bin/nnc/coco.c b/bin/nnc/coco.c
index db02cbf13..dbe27462a 100644
--- a/bin/nnc/coco.c
+++ b/bin/nnc/coco.c
@@ -27,23 +27,23 @@ static ccv_cnnp_model_t* _resnet_block_new(const int filters, const int expansio
 			ccv_cnnp_model_t* const avgdown = ccv_cnnp_average_pool(DIM_ALLOC(strides, strides), HINT((strides, strides), (0, 0)), 0);
 			shortcut = ccv_cnnp_model_apply(avgdown, MODEL_IO_LIST(input));
 		}
-		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
+		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
 		shortcut = ccv_cnnp_model_apply(conv0, MODEL_IO_LIST(shortcut));
 	}
 	ccv_cnnp_model_t* const conv1 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(conv1, MODEL_IO_LIST(input));
 	ccv_cnnp_model_t* const conv2 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv2, MODEL_IO_LIST(output));
 	ccv_cnnp_model_t* const conv3 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv3, MODEL_IO_LIST(output));
@@ -72,13 +72,13 @@ ccv_array_t* _imagenet_resnet50_v1d(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0)
@@ -110,14 +110,14 @@ ccv_array_t* _imagenet_resnet50_v1d(void)
 static void _fpn(const int d, const ccv_cnnp_model_io_t* const c, const int c_size, ccv_cnnp_model_io_t* const p)
 {
 	int i;
-	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[c_size - 1]));
+	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[c_size - 1]));
 	p[c_size - 1] = output;
 	for (i = c_size - 2; i >= 0; i--)
 	{
-		const ccv_cnnp_model_io_t lateral = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[i]));
+		const ccv_cnnp_model_io_t lateral = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[i]));
 		const ccv_cnnp_model_io_t up = ccv_cnnp_model_apply(ccv_cnnp_upsample(CCV_NNC_UPSAMPLE_BILINEAR, 2, 2, 0), MODEL_IO_LIST(output));
 		const ccv_cnnp_model_io_t sum = ccv_cnnp_model_apply(ccv_cnnp_sum(0), MODEL_IO_LIST(lateral, up));
-		output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(sum));
+		output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(sum));
 		p[i] = output;
 	}
 }
@@ -126,13 +126,13 @@ ccv_array_t* _imagenet_resnet50_v1d_fpn(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0)
@@ -171,7 +171,7 @@ ccv_cnnp_model_t* _coco_resnet50_v1d_rpn(void)
 	ccv_cnnp_model_io_t proposals[5];
 	int i;
 	// 3 aspect ratios (1:2, 1:1, 2:1). Each has 4 + 1 (x, y, w, h, objectness), total 15.
-	ccv_cnnp_model_t* const rpn_proposals = ccv_cnnp_convolution(1, 15, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, "rpn");
+	ccv_cnnp_model_t* const rpn_proposals = ccv_cnnp_convolution(1, 15, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, "rpn");
 	for (i = 0; i < 5; i++)
 	{
 		p[i] = ccv_cnnp_input();
diff --git a/bin/nnc/imagenet.c b/bin/nnc/imagenet.c
index a06e7fd01..a0d44dcad 100644
--- a/bin/nnc/imagenet.c
+++ b/bin/nnc/imagenet.c
@@ -26,23 +26,23 @@ static ccv_cnnp_model_t* _resnet_block_new(const int filters, const int expansio
 			ccv_cnnp_model_t* const avgdown = ccv_cnnp_average_pool(DIM_ALLOC(strides, strides), HINT((strides, strides), (0, 0)), 0);
 			shortcut = ccv_cnnp_model_apply(avgdown, MODEL_IO_LIST(input));
 		}
-		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
+		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
 		shortcut = ccv_cnnp_model_apply(conv0, MODEL_IO_LIST(shortcut));
 	}
 	ccv_cnnp_model_t* const conv1 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(conv1, MODEL_IO_LIST(input));
 	ccv_cnnp_model_t* const conv2 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv2, MODEL_IO_LIST(output));
 	ccv_cnnp_model_t* const conv3 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv3, MODEL_IO_LIST(output));
@@ -71,13 +71,13 @@ ccv_cnnp_model_t* _imagenet_resnet50_v1d(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0)
@@ -98,13 +98,13 @@ ccv_cnnp_model_t* _imagenet_resnet101_v1d(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0)
@@ -124,29 +124,29 @@ ccv_cnnp_model_t* _imagenet_resnet101_v1d(void)
 ccv_cnnp_model_t* _imagenet_vgg13(void)
 {
 	ccv_cnnp_model_t* vgg13 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0),
-		ccv_cnnp_convolution(1, 128, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 128, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 128, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 128, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0),
-		ccv_cnnp_convolution(1, 256, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 256, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 256, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 256, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0),
-		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0),
-		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 512, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(0, 0), ccv_nnc_no_hint, 0),
 		ccv_cnnp_flatten(0),
@@ -165,7 +165,7 @@ static ccv_cnnp_model_t* _mconv_block_new(const int kernel_size, const int strid
 	{
 		expand_filters = input_filters * expand_ratio;
 		ccv_cnnp_model_t* const expand_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-			ccv_cnnp_convolution(1, expand_filters, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
+			ccv_cnnp_convolution(1, expand_filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
 			ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 			ccv_cnnp_swish(0)
 		), 1, 0);
@@ -173,7 +173,7 @@ static ccv_cnnp_model_t* _mconv_block_new(const int kernel_size, const int strid
 	}
 	const int paddings = (kernel_size - 1) / 2;
 	ccv_cnnp_model_t* const depthwise_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(expand_filters, expand_filters, DIM_ALLOC(kernel_size, kernel_size), 1, HINT((strides, strides), (paddings, paddings)), 0, 1, 0),
+		ccv_cnnp_convolution(expand_filters, expand_filters, DIM_ALLOC(kernel_size, kernel_size), DIM_ALLOC(), 1, HINT((strides, strides), (paddings, paddings)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_swish(0)
 	), 1, 0);
@@ -181,15 +181,15 @@ static ccv_cnnp_model_t* _mconv_block_new(const int kernel_size, const int strid
 	const int se_filters = ccv_max(1, (int)(input_filters * se_ratio + 0.5));
 	ccv_cnnp_model_t* const se_conv = ccv_cnnp_sequential_new(MODEL_LIST(
 		ccv_cnnp_average_pool(DIM_ALLOC(0, 0), ccv_nnc_no_hint, 0),
-		ccv_cnnp_convolution(1, se_filters, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, se_filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_swish(0),
-		ccv_cnnp_convolution(1, expand_filters, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, expand_filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_sigmoid(0)
 	), 1, 0);
 	const ccv_cnnp_model_io_t se = ccv_cnnp_model_apply(se_conv, MODEL_IO_LIST(x));
 	x = ccv_cnnp_model_apply(ccv_cnnp_mul(1, 0), MODEL_IO_LIST(x, se));
 	ccv_cnnp_model_t* const proj_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, output_filters, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, output_filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0)
 	), 1, 0);
 	x = ccv_cnnp_model_apply(proj_conv, MODEL_IO_LIST(x));
@@ -221,7 +221,7 @@ ccv_cnnp_model_t* _efficientnet_b0(void)
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	const float dropout = 0.1;
 	ccv_cnnp_model_t* const init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_swish(0)
 	), 1, 0);
@@ -234,7 +234,7 @@ ccv_cnnp_model_t* _efficientnet_b0(void)
 	output = ccv_cnnp_model_apply(_mconv_block_layer_new(4, 5, 2, 6, 112, 192, 0.25, dropout), MODEL_IO_LIST(output));
 	output = ccv_cnnp_model_apply(_mconv_block_layer_new(1, 3, 1, 6, 192, 320, 0.25, dropout), MODEL_IO_LIST(output));
 	ccv_cnnp_model_t* const head_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 1280, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 1280, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_swish(0)
 	), 1, 0);
diff --git a/lib/nnc/ccv_cnnp_model_addons.c b/lib/nnc/ccv_cnnp_model_addons.c
index 61c0f9368..8b3d4a9fd 100644
--- a/lib/nnc/ccv_cnnp_model_addons.c
+++ b/lib/nnc/ccv_cnnp_model_addons.c
@@ -897,6 +897,7 @@ typedef struct {
 	int groups;
 	int filters;
 	int kdim[CCV_NNC_MAX_DIM_ALLOC];
+	int dilation[CCV_NNC_MAX_DIM_ALLOC];
 	int no_bias;
 	int format;
 	ccv_nnc_hint_t hint;
@@ -931,7 +932,11 @@ static void _ccv_cnnp_convolution_build(ccv_cnnp_model_t* const super, ccv_nnc_s
 	ccv_nnc_cmd_t cmd = CMD_CONVOLUTION_FORWARD(self->groups, self->filters);
 	for (i = 0; i < CCV_NNC_MAX_DIM; i++)
 		cmd.info.size.dim[i] = self->kdim[i];
+	memcpy(cmd.info.convolution.dilation, self->dilation, sizeof(self->dilation));
 	ccv_nnc_tensor_param_t output_params;
+	// Dilate weight size based on the dilation factor.
+	for (i = 0; i < CCV_NNC_MAX_DIM; i++)
+		weights_params.dim[i + hw] = (self->kdim[i] - 1) * ccv_max(self->dilation[i], 1) + 1;
 	ccv_nnc_hint_tensor_auto(cmd, (ccv_nnc_tensor_param_t []){
 			params,
 			weights_params,
@@ -980,7 +985,7 @@ static const ccv_cnnp_model_vtab_t ccv_cnnp_convolution_isa = {
 	.copy = _ccv_cnnp_convolution_copy,
 };
 
-ccv_cnnp_model_t* ccv_cnnp_convolution(const int groups, const int filters, const int kdim[CCV_NNC_MAX_DIM_ALLOC], const int no_bias, ccv_nnc_hint_t hint, const int format, const int is_trainable, const char* const name)
+ccv_cnnp_model_t* ccv_cnnp_convolution(const int groups, const int filters, const int kdim[CCV_NNC_MAX_DIM_ALLOC], const int dilation[CCV_NNC_MAX_DIM_ALLOC], const int no_bias, ccv_nnc_hint_t hint, const int format, const int is_trainable, const char* const name)
 {
 	ccv_cnnp_model_convolution_t* const model_convolution = (ccv_cnnp_model_convolution_t*)cccalloc(1, sizeof(ccv_cnnp_model_convolution_t));
 	model_convolution->super.isa = &ccv_cnnp_convolution_isa;
@@ -996,6 +1001,7 @@ ccv_cnnp_model_t* ccv_cnnp_convolution(const int groups, const int filters, cons
 	model_convolution->groups = groups;
 	model_convolution->filters = filters;
 	memcpy(model_convolution->kdim, kdim, sizeof(model_convolution->kdim));
+	memcpy(model_convolution->dilation, dilation, sizeof(model_convolution->dilation));
 	model_convolution->no_bias = no_bias;
 	model_convolution->hint = hint;
 	model_convolution->format = format;
@@ -1005,7 +1011,7 @@ ccv_cnnp_model_t* ccv_cnnp_convolution(const int groups, const int filters, cons
 static ccv_cnnp_model_t* _ccv_cnnp_convolution_copy(const ccv_cnnp_model_t* const super, void* const context)
 {
 	ccv_cnnp_model_convolution_t* const self = (ccv_cnnp_model_convolution_t*)super;
-	return ccv_cnnp_convolution(self->groups, self->filters, self->kdim, self->no_bias, self->hint, self->format, self->super.is_trainable, self->super.name);
+	return ccv_cnnp_convolution(self->groups, self->filters, self->kdim, self->dilation, self->no_bias, self->hint, self->format, self->super.is_trainable, self->super.name);
 }
 
 // MARK - Dense Layer
diff --git a/lib/nnc/ccv_nnc.h b/lib/nnc/ccv_nnc.h
index 72b6b9c73..69a931795 100644
--- a/lib/nnc/ccv_nnc.h
+++ b/lib/nnc/ccv_nnc.h
@@ -4111,6 +4111,7 @@ CCV_WARN_UNUSED(ccv_cnnp_model_t*) ccv_cnnp_concat(const int axis, const char* c
  * @param groups The number of kernel groups in the model.
  * @param filters The total number of filters in the model (filters = groups * per group filters).
  * @param kdim The dimensions of the kernel.
+ * @param dilation The dilation factor on each dimension.
  * @param no_bias Whether has bias term or not.
  * @param hint The hint for alignment.
  * @param format The format for weights. If 0, it will have the same format as the input.
@@ -4118,7 +4119,7 @@ CCV_WARN_UNUSED(ccv_cnnp_model_t*) ccv_cnnp_concat(const int axis, const char* c
  * @param name The unique name of the model.
  * @return A convolution model.
  */
-CCV_WARN_UNUSED(ccv_cnnp_model_t*) ccv_cnnp_convolution(const int groups, const int filters, const int kdim[CCV_NNC_MAX_DIM_ALLOC], const int no_bias, ccv_nnc_hint_t hint, const int format, const int is_trainable, const char* const name);
+CCV_WARN_UNUSED(ccv_cnnp_model_t*) ccv_cnnp_convolution(const int groups, const int filters, const int kdim[CCV_NNC_MAX_DIM_ALLOC], const int dilation[CCV_NNC_MAX_DIM_ALLOC], const int no_bias, ccv_nnc_hint_t hint, const int format, const int is_trainable, const char* const name);
 /**
  * A dense layer model.
  * @param count The output dimension.
diff --git a/test/int/nnc/cifar.tests.c b/test/int/nnc/cifar.tests.c
index 9705c3358..a0935fe22 100644
--- a/test/int/nnc/cifar.tests.c
+++ b/test/int/nnc/cifar.tests.c
@@ -16,7 +16,7 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 {
 	ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
@@ -27,13 +27,13 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 	{
 		ccv_cnnp_model_io_t shortcut = output;
 		ccv_cnnp_model_t* res1 = ccv_cnnp_sequential_new(MODEL_LIST(
-			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 			ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 			ccv_cnnp_relu(0)
 		), 1, 0);
 		output = ccv_cnnp_model_apply(res1, MODEL_IO_LIST(output));
 		ccv_cnnp_model_t* res2 = ccv_cnnp_sequential_new(MODEL_LIST(
-			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+			ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 			ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 			ccv_cnnp_relu(0)
 		), 1, 0);
@@ -47,7 +47,7 @@ static ccv_cnnp_model_t* _dawn_layer_new(const int filters, const int strides, c
 static ccv_cnnp_model_t* _cifar_10_dawn(const int softmax)
 {
 	ccv_cnnp_model_t* prep = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
diff --git a/test/unit/nnc/cnnp.core.tests.c b/test/unit/nnc/cnnp.core.tests.c
index da96356aa..21765a60d 100644
--- a/test/unit/nnc/cnnp.core.tests.c
+++ b/test/unit/nnc/cnnp.core.tests.c
@@ -14,13 +14,13 @@ TEST_SETUP()
 static ccv_cnnp_model_t* simple_cifar_10(void)
 {
 	return ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
 		ccv_cnnp_flatten(0),
@@ -109,22 +109,22 @@ TEST_CASE("inception layer for model")
 {
 	const ccv_cnnp_model_io_t x = ccv_cnnp_input();
 	_ccv_cnnp_model_notified = 0;
-	ccv_cnnp_model_t* const conv_1 = ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0);
+	ccv_cnnp_model_t* const conv_1 = ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0);
 	ccv_cnnp_model_notify_hook(conv_1, _ccv_cnnp_model_hook, 0);
 	ccv_cnnp_model_io_t tower_1 = ccv_cnnp_model_apply(conv_1, MODEL_IO_LIST(x));
 	ccv_cnnp_model_t* const relu_1 = ccv_cnnp_relu(0);
 	ccv_cnnp_model_notify_hook(relu_1, _ccv_cnnp_model_hook, 0);
 	tower_1 = ccv_cnnp_model_apply(relu_1, MODEL_IO_LIST(tower_1));
-	tower_1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(tower_1));
+	tower_1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(tower_1));
 	tower_1 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(tower_1));
 
-	ccv_cnnp_model_io_t tower_2 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(x));
+	ccv_cnnp_model_io_t tower_2 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(x));
 	tower_2 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(tower_2));
-	tower_2 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0), MODEL_IO_LIST(tower_2));
+	tower_2 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0), MODEL_IO_LIST(tower_2));
 	tower_2 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(tower_2));
 
 	ccv_cnnp_model_io_t tower_3 = ccv_cnnp_model_apply(ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((1, 1), (1, 1)), 0), MODEL_IO_LIST(x));
-	tower_3 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(tower_3));
+	tower_3 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(tower_3));
 	tower_3 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(tower_3));
 	ccv_cnnp_model_t* const add_1 = ccv_cnnp_sum(0);
 	ccv_cnnp_model_notify_hook(add_1, _ccv_cnnp_model_hook, 0);
@@ -145,16 +145,16 @@ static ccv_cnnp_model_t* _ccv_multiple_outputs_functional_model(const ccv_nnc_te
 {
 	ccv_cnnp_model_io_t input0 = ccv_cnnp_input();
 	ccv_cnnp_model_io_t input1 = ccv_cnnp_input();
-	ccv_cnnp_model_io_t output0 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(input0));
+	ccv_cnnp_model_io_t output0 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(input0));
 	output0 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(output0));
-	ccv_cnnp_model_io_t output1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(input1));
+	ccv_cnnp_model_io_t output1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(input1));
 	output1 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(output1));
 	ccv_cnnp_model_t* model0 = ccv_cnnp_model_new(MODEL_IO_LIST(input0, input1), MODEL_IO_LIST(output0, output1), 1, 0);
 	input0 = ccv_cnnp_input();
 	input1 = ccv_cnnp_input();
 	output0 = ccv_cnnp_model_apply(model0, MODEL_IO_LIST(input0, input1));
 	ccv_cnnp_model_io_t input2 = ccv_cnnp_input();
-	output1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0), MODEL_IO_LIST(input2));
+	output1 = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0), MODEL_IO_LIST(input2));
 	output1 = ccv_cnnp_model_apply(ccv_cnnp_relu(0), MODEL_IO_LIST(output1));
 	ccv_cnnp_model_t* interim = ccv_cnnp_model_new(MODEL_IO_LIST(input0, input1, input2), MODEL_IO_LIST(output0, output1), 1, 0);
 	input0 = ccv_cnnp_input();
@@ -349,13 +349,13 @@ TEST_CASE("train model with share weights and L2 loss")
 static ccv_cnnp_model_t* simple_cifar_10_no_softmax(void)
 {
 	return ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(5, 5), DIM_ALLOC(), 0, HINT((1, 1), (2, 2)), 0, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_average_pool(DIM_ALLOC(3, 3), HINT((2, 2), (0, 0)), 0),
 		ccv_cnnp_flatten(0),
@@ -1369,23 +1369,23 @@ static ccv_cnnp_model_t* _resnet_block_new(const int filters, const int expansio
 	{
 		ccv_cnnp_model_t* const avgdown = ccv_cnnp_average_pool(DIM_ALLOC(strides, strides), HINT((strides, strides), (0, 0)), 0);
 		shortcut = ccv_cnnp_model_apply(avgdown, MODEL_IO_LIST(input));
-		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
+		ccv_cnnp_model_t* const conv0 = ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 1, HINT((1, 1), (0, 0)), 0, 1, 0);
 		shortcut = ccv_cnnp_model_apply(conv0, MODEL_IO_LIST(shortcut));
 	}
 	ccv_cnnp_model_t* const conv1 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(conv1, MODEL_IO_LIST(input));
 	ccv_cnnp_model_t* const conv2 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((strides, strides), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv2, MODEL_IO_LIST(output));
 	ccv_cnnp_model_t* const conv3 = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
+		ccv_cnnp_convolution(1, filters * expansion, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0)
 	), 1, 0);
 	output = ccv_cnnp_model_apply(conv3, MODEL_IO_LIST(output));
@@ -1413,14 +1413,14 @@ static ccv_cnnp_model_t* _resnet_block_layer_new(const int filters, const int ex
 static void _fpn(const int d, const ccv_cnnp_model_io_t* const c, const int c_size, ccv_cnnp_model_io_t* const p)
 {
 	int i;
-	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[c_size - 1]));
+	ccv_cnnp_model_io_t output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[c_size - 1]));
 	p[c_size - 1] = output;
 	for (i = c_size - 2; i >= 0; i--)
 	{
-		const ccv_cnnp_model_io_t lateral = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[i]));
+		const ccv_cnnp_model_io_t lateral = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, 0), MODEL_IO_LIST(c[i]));
 		const ccv_cnnp_model_io_t up = ccv_cnnp_model_apply(ccv_cnnp_upsample(CCV_NNC_UPSAMPLE_BILINEAR, 2, 2, 0), MODEL_IO_LIST(output));
 		const ccv_cnnp_model_io_t sum = ccv_cnnp_model_apply(ccv_cnnp_sum(0), MODEL_IO_LIST(lateral, up));
-		output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(sum));
+		output = ccv_cnnp_model_apply(ccv_cnnp_convolution(1, d, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0), MODEL_IO_LIST(sum));
 		p[i] = output;
 	}
 }
@@ -1429,13 +1429,13 @@ ccv_cnnp_model_t* _imagenet_resnet50_v1d_fpn(void)
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
 	ccv_cnnp_model_t* init_conv = ccv_cnnp_sequential_new(MODEL_LIST(
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((2, 2), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
-		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
+		ccv_cnnp_convolution(1, 64, DIM_ALLOC(3, 3), DIM_ALLOC(), 1, HINT((1, 1), (1, 1)), 0, 1, 0),
 		ccv_cnnp_batch_norm(0.9, 1e-4, 1, 0),
 		ccv_cnnp_relu(0),
 		ccv_cnnp_max_pool(DIM_ALLOC(3, 3), HINT((2, 2), (1, 1)), 0)
@@ -1454,7 +1454,7 @@ ccv_cnnp_model_t* _imagenet_resnet50_v1d_fpn(void)
 	_fpn(256, c, 4, p);
 	p[4] = ccv_cnnp_model_apply(ccv_cnnp_average_pool(DIM_ALLOC(2, 2), HINT((2, 2), (0, 0)), 0), MODEL_IO_LIST(p[3]));
 	// 3 aspect ratios (1:2, 1:1, 2:1). Each has 4 + 2 (x, y, w, h, object, non-object), total 18.
-	ccv_cnnp_model_t* const rpn_proposals = ccv_cnnp_convolution(1, 18, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, "rpn");
+	ccv_cnnp_model_t* const rpn_proposals = ccv_cnnp_convolution(1, 18, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, "rpn");
 	ccv_cnnp_model_io_t proposals[5];
 	int i;
 	for (i = 0; i < 5; i++)
@@ -1657,9 +1657,9 @@ TEST_CASE("LoRA fine-tuning GEMM set is_trainable to false")
 TEST_CASE("LoRA fine-tuning convolution set is_trainable to false")
 {
 	const ccv_cnnp_model_io_t input = ccv_cnnp_input();
-	ccv_cnnp_model_t* const conv = ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, -1, "conv");
-	ccv_cnnp_model_t* const down = ccv_cnnp_convolution(1, 4, DIM_ALLOC(3, 3), 0, HINT((1, 1), (1, 1)), 0, 1, "down");
-	ccv_cnnp_model_t* const up = ccv_cnnp_convolution(1, 32, DIM_ALLOC(1, 1), 0, HINT((1, 1), (0, 0)), 0, 1, "up");
+	ccv_cnnp_model_t* const conv = ccv_cnnp_convolution(1, 32, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, -1, "conv");
+	ccv_cnnp_model_t* const down = ccv_cnnp_convolution(1, 4, DIM_ALLOC(3, 3), DIM_ALLOC(), 0, HINT((1, 1), (1, 1)), 0, 1, "down");
+	ccv_cnnp_model_t* const up = ccv_cnnp_convolution(1, 32, DIM_ALLOC(1, 1), DIM_ALLOC(), 0, HINT((1, 1), (0, 0)), 0, 1, "up");
 	ccv_cnnp_model_io_t out = ccv_cnnp_model_apply(conv, MODEL_IO_LIST(input));
 	ccv_cnnp_model_io_t out_down = ccv_cnnp_model_apply(down, MODEL_IO_LIST(input));
 	ccv_cnnp_model_io_t out_up = ccv_cnnp_model_apply(up, MODEL_IO_LIST(out_down));