metal: add col2im_1d op (f32/f16/bf16) (#25176)
* metal: add col2im_1d op (f32/f16/bf16) Gather kernel mirroring the CPU/CUDA path: each output (t_out, oc) reads its ceil(K/s0) source columns with an F32 accumulator, a single write and no atomics. One thread per output element, 256 per threadgroup. * metal: check dst contiguity and type match in supports_op for COL2IM_1D Align the GGML_OP_COL2IM_1D predicate with the CPU, CUDA, and Vulkan backends: the kernel writes dst with linear indexing and assumes the same type as src0, so supports_op must also require a contiguous dst and op->type == op->src[0]->type. * Update ggml/src/ggml-metal/ggml-metal.metal Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com> --------- Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>
This commit is contained in:
@@ -603,6 +603,16 @@ typedef struct {
|
||||
uint64_t nb1;
|
||||
} ggml_metal_kargs_conv_transpose_1d;
|
||||
|
||||
typedef struct {
|
||||
int32_t T_in;
|
||||
int32_t T_out;
|
||||
int32_t OC;
|
||||
int32_t K;
|
||||
int32_t K_OC;
|
||||
int32_t s0;
|
||||
int32_t p0;
|
||||
} ggml_metal_kargs_col2im_1d;
|
||||
|
||||
typedef struct {
|
||||
int32_t IC;
|
||||
int32_t IH;
|
||||
|
||||
Reference in New Issue
Block a user