metal: add col2im_1d op (f32/f16/bf16) (#25176)

This commit is contained in:
Georgi Gerganov
2026-07-08 16:50:17 +03:00
parent 5dca9f3470
commit 400d4bf0e2
+42
View File
@@ -118,6 +118,48 @@ kernel void kernel_im2col_ext(
template [[host_name("kernel_im2col_ext_f32")]] kernel im2col_ext_t kernel_im2col_ext<float>;
template [[host_name("kernel_im2col_ext_f16")]] kernel im2col_ext_t kernel_im2col_ext<half>;
template <typename T>
kernel void kernel_col2im_1d(
constant ggml_metal_kargs_col2im_1d & args,
device const T * col,
device T * dst,
uint tgpig [[threadgroup_position_in_grid]],
uint tpitg [[thread_position_in_threadgroup]],
uint ntg [[threads_per_threadgroup]]) {
const int idx = tgpig * ntg + tpitg;
if (idx >= args.T_out * args.OC) {
return;
}
const int t_out = idx % args.T_out;
const int oc = idx / args.T_out;
const int t_abs = t_out + args.p0; // absolute position in uncropped signal
int t_in_min = (t_abs - args.K + args.s0) / args.s0; // ceil((t_abs - K + 1) / s0)
if (t_in_min < 0) {
t_in_min = 0;
}
int t_in_max = t_abs / args.s0;
if (t_in_max >= args.T_in) {
t_in_max = args.T_in - 1;
}
float sum = 0.0f;
for (int t_in = t_in_min; t_in <= t_in_max; t_in++) {
const int k = t_abs - t_in * args.s0;
sum += float(col[(oc * args.K + k) + t_in * args.K_OC]);
}
dst[t_out + oc * args.T_out] = T(sum);
}
template [[host_name("kernel_col2im_1d_f32")]] kernel void kernel_col2im_1d<float>(constant ggml_metal_kargs_col2im_1d &, device const float *, device float *, uint, uint, uint);
template [[host_name("kernel_col2im_1d_f16")]] kernel void kernel_col2im_1d<half>(constant ggml_metal_kargs_col2im_1d &, device const half *, device half *, uint, uint, uint);
#if defined(GGML_METAL_HAS_BF16)
template [[host_name("kernel_col2im_1d_bf16")]] kernel void kernel_col2im_1d<bfloat>(constant ggml_metal_kargs_col2im_1d &, device const bfloat *, device bfloat *, uint, uint, uint);
#endif
template <typename TK>
kernel void kernel_conv_2d(
constant ggml_metal_kargs_conv_2d & args,