Kcpp triage for rowsplit: revert ggml-org#16715 until ggml-org#16799 is resolved

revert ggml-org#16715 (+2 squashed commit)

Squashed commit:

[289af2ee2] Revert "Hide latency of bias and gate-loading (ggml-org#16847)"

This reverts commit 8b11dee.

[a3e5c1e95] Revert "CUDA: add unused vars to mmvf and mmvq (ggml-org#16807)"

This reverts commit 463bbf2.

Author: LostRuins

ggml/src/ggml-cuda/common.cuh

@@ -1013,16 +1013,3 @@ struct ggml_backend_cuda_context {
         return pool(device);
     }
 };
-
-struct ggml_cuda_mm_fusion_args_host {
-    const ggml_tensor * x_bias = nullptr;
-    const ggml_tensor * gate = nullptr;
-    const ggml_tensor * gate_bias = nullptr;
-    ggml_glu_op glu_op;
-};
-struct ggml_cuda_mm_fusion_args_device {
-    const void * x_bias = nullptr;
-    const void * gate = nullptr;
-    const void * gate_bias = nullptr;
-    ggml_glu_op glu_op;
-};

ggml/src/ggml-cuda/convert.cuh

@@ -1,4 +1,3 @@
-#pragma once
 #include "common.cuh"
 
 #define CUDA_DEQUANTIZE_BLOCK_SIZE 256