@@ -5215,9 +5215,9 @@ static void ggml_vk_quantize_q8_1(ggml_backend_vk_context * ctx, vk_context& sub
5215
5215
}
5216
5216
5217
5217
static void ggml_vk_mul_mat_q_f16(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, bool dryrun = false) {
5218
- VK_LOG_DEBUG("ggml_vk_mul_mat_q_f16((" << src0 << ", name=" << src0->name << ", type=" << src0->type << ", ne0=" << src0->ne[0] << ", ne1=" << src0->ne[1] << ", ne2=" << src0->ne[2] << ", ne3=" << src0->ne[3] << ", nb0=" << src0->nb[0] << ", nb1=" << src0->nb[1] << ", nb2=" << src0->nb[2] << ", nb3=" << src0->nb[3];
5219
- std::cerr << "), (" << src1 << ", name=" << src1->name << ", type=" << src1->type << ", ne0=" << src1->ne[0] << ", ne1=" << src1->ne[1] << ", ne2=" << src1->ne[2] << ", ne3=" << src1->ne[3] << ", nb0=" << src1->nb[0] << ", nb1=" << src1->nb[1] << ", nb2=" << src1->nb[2] << ", nb3=" << src1->nb[3];
5220
- std::cerr << "), (" << dst << ", name=" << dst->name << ", type=" << dst->type << ", ne0=" << dst->ne[0] << ", ne1=" << dst->ne[1] << ", ne2=" << dst->ne[2] << ", ne3=" << dst->ne[3] << ", nb0=" << dst->nb[0] << ", nb1=" << dst->nb[1] << ", nb2=" << dst->nb[2] << ", nb3=" << dst->nb[3];
5218
+ VK_LOG_DEBUG("ggml_vk_mul_mat_q_f16((" << src0 << ", name=" << src0->name << ", type=" << ggml_type_name( src0->type) << ", ne0=" << src0->ne[0] << ", ne1=" << src0->ne[1] << ", ne2=" << src0->ne[2] << ", ne3=" << src0->ne[3] << ", nb0=" << src0->nb[0] << ", nb1=" << src0->nb[1] << ", nb2=" << src0->nb[2] << ", nb3=" << src0->nb[3];
5219
+ std::cerr << "), (" << src1 << ", name=" << src1->name << ", type=" << ggml_type_name( src1->type) << ", ne0=" << src1->ne[0] << ", ne1=" << src1->ne[1] << ", ne2=" << src1->ne[2] << ", ne3=" << src1->ne[3] << ", nb0=" << src1->nb[0] << ", nb1=" << src1->nb[1] << ", nb2=" << src1->nb[2] << ", nb3=" << src1->nb[3];
5220
+ std::cerr << "), (" << dst << ", name=" << dst->name << ", type=" << ggml_type_name( dst->type) << ", ne0=" << dst->ne[0] << ", ne1=" << dst->ne[1] << ", ne2=" << dst->ne[2] << ", ne3=" << dst->ne[3] << ", nb0=" << dst->nb[0] << ", nb1=" << dst->nb[1] << ", nb2=" << dst->nb[2] << ", nb3=" << dst->nb[3];
5221
5221
std::cerr << "), " << (dryrun ? "dryrun" : "") << ")");
5222
5222
GGML_ASSERT(ggml_vk_dim01_contiguous(src0) || src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16 || src0->type == GGML_TYPE_BF16); // NOLINT
5223
5223
GGML_ASSERT(ggml_vk_dim01_contiguous(src1) || src1->type == GGML_TYPE_F32 || src1->type == GGML_TYPE_F16); // NOLINT
@@ -11267,7 +11267,7 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph *
11267
11267
tensor_clone = ggml_upscale_ext(ggml_ctx, src_clone[0], tensor->ne[0], tensor->ne[1], tensor->ne[2], tensor->ne[3], (ggml_scale_mode) tensor->op_params[0]);
11268
11268
} else if (tensor->op == GGML_OP_SCALE) {
11269
11269
const float * params = (const float *)tensor->op_params;
11270
- tensor_clone = ggml_scale (ggml_ctx, src_clone[0], params[0]);
11270
+ tensor_clone = ggml_scale_bias (ggml_ctx, src_clone[0], params[0], params[1 ]);
11271
11271
} else if (tensor->op == GGML_OP_SQR) {
11272
11272
tensor_clone = ggml_sqr(ggml_ctx, src_clone[0]);
11273
11273
} else if (tensor->op == GGML_OP_SIN) {
@@ -11379,7 +11379,7 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph *
11379
11379
tensor_clone = ggml_cpy(ggml_ctx, src_clone[0], src_clone[1]);
11380
11380
}
11381
11381
} else if (tensor->op == GGML_OP_SET_ROWS) {
11382
- tensor_clone = ggml_set_rows(ggml_ctx, src_clone[0], src_clone[1]);
11382
+ tensor_clone = ggml_set_rows(ggml_ctx, src_clone[0], src_clone[1], src_clone[2] );
11383
11383
} else if (tensor->op == GGML_OP_CONT) {
11384
11384
tensor_clone = ggml_cont_4d(ggml_ctx, src_clone[0], tensor->ne[0], tensor->ne[1], tensor->ne[2], tensor->ne[3]);
11385
11385
} else if (tensor->op == GGML_OP_RESHAPE) {
0 commit comments