LLM inference in C/C++
C++ ggml
webgpu: format the GET_ROWS case block (#28542)
Pascalc0b1871bc7e4
diff --git a/ggml/src/ggml-webgpu/ggml-webgpu.cpp b/ggml/src/ggml-webgpu/ggml-webgpu.cppindex 2e6c5a8c5e..f06a9c872d 100644--- a/ggml/src/ggml-webgpu/ggml-webgpu.cpp+++ b/ggml/src/ggml-webgpu/ggml-webgpu.cpp@@ -4323,21 +4323,23 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, constop->type == GGML_TYPE_Q4_0) &&src0->type == GGML_TYPE_F32 && (src1->type == GGML_TYPE_I64 || src1->type == GGML_TYPE_I32));break;- case GGML_OP_GET_ROWS: {- const size_t storage_alignment =- ctx->webgpu_global_ctx->capabilities.limits.minStorageBufferOffsetAlignment;- const size_t src_address_unit =- src0->type == GGML_TYPE_F32 && op->ne[0] % 4 == 0 ? 4 * sizeof(float) : ggml_type_size(src0->type);- if (ggml_webgpu_tensor_misalignment(src0, storage_alignment) % src_address_unit != 0) {+ case GGML_OP_GET_ROWS:+ {+ const size_t storage_alignment =+ ctx->webgpu_global_ctx->capabilities.limits.minStorageBufferOffsetAlignment;+ const size_t src_address_unit =+ src0->type == GGML_TYPE_F32 && op->ne[0] % 4 == 0 ? 4 * sizeof(float) : ggml_type_size(src0->type);+ if (ggml_webgpu_tensor_misalignment(src0, storage_alignment) % src_address_unit != 0) {+ break;+ }+ if (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16 ||+ ggml_webgpu_supported_qtype(src0->type)) {+ supports_op = (op->type == GGML_TYPE_F32);+ } else if (src0->type == GGML_TYPE_I32) {+ supports_op = op->type == GGML_TYPE_I32;+ }break;}- if (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16 || ggml_webgpu_supported_qtype(src0->type)) {- supports_op = (op->type == GGML_TYPE_F32);- } else if (src0->type == GGML_TYPE_I32) {- supports_op = op->type == GGML_TYPE_I32;- }- break;- }case GGML_OP_MUL_MAT:{switch (src1->type) {