diff --git a/ggml/src/ggml-cuda/fattn.cu b/ggml/src/ggml-cuda/fattn.cu
index 195904ee20..721edd9994 100644
--- a/ggml/src/ggml-cuda/fattn.cu
+++ b/ggml/src/ggml-cuda/fattn.cu
@@ -310,8 +310,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
         }
     }
 
-    const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));
-
     const int cc = ggml_cuda_info().devices[device].cc;
 
     switch (K->ne[0]) {
@@ -334,9 +332,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
             if (!gqa_opt_applies) {
                 return BEST_FATTN_KERNEL_NONE;
             }
-            if (!V_is_K_view) {
-                return BEST_FATTN_KERNEL_NONE;
-            }
             break;
         default:
             return BEST_FATTN_KERNEL_NONE;
diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp
index b3198b7e3a..16d42c4ae3 100644
--- a/src/llama-graph.cpp
+++ b/src/llama-graph.cpp
@@ -1630,11 +1630,6 @@ ggml_tensor * llm_graph_context::build_attn_mha(
                                   hparams.attn_soft_cap ? hparams.f_attn_logit_softcapping : 0.0f);
         cb(cur, LLAMA_TENSOR_NAME_FATTN, il);
 
-        if (!cparams.offload_kqv) {
-            // all nodes between the KV store and the attention output are run on the CPU
-            ggml_backend_sched_set_tensor_backend(sched, cur, backend_cpu);
-        }
-
         ggml_flash_attn_ext_add_sinks(cur, sinks);
         ggml_flash_attn_ext_set_prec (cur, GGML_PREC_F32);