diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index a391717e3..eb43520f9 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -8806,6 +8806,7 @@ class GraniteMoeModel(GraniteModel):
             gate, up = data_torch.split(ffn_dim, dim=-2)
             yield from ModelBase.modify_tensors(self, gate, self.format_tensor_name(gguf.MODEL_TENSOR.FFN_GATE_EXP, bid), bid)
             yield from ModelBase.modify_tensors(self, up, self.format_tensor_name(gguf.MODEL_TENSOR.FFN_UP_EXP, bid), bid)
+            return
 
         has_experts = bool(self.hparams.get('num_local_experts'))
 
diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp
index cc8bc6068..e20d8e263 100644
--- a/src/llama-kv-cache.cpp
+++ b/src/llama-kv-cache.cpp
@@ -1772,8 +1772,6 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
     io.write(&v_trans, sizeof(v_trans));
     io.write(&n_layer, sizeof(n_layer));
 
-    std::vector<uint8_t> tmp_buf;
-
     // Iterate and write all the keys first, each row is a cell
     // Get whole range at a time
     for (const auto & layer : layers) {
@@ -1791,7 +1789,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
         const uint64_t k_size_row = ggml_row_size(k->type, n_embd_k_gqa);
         io.write(&k_size_row, sizeof(k_size_row));
 
-        // Read each range of cells of k_size length each into tmp_buf and write out
+        // Read each range of cells of k_size length and write out
         for (const auto & range : cr.data) {
             const size_t range_size = range.second - range.first;
             const size_t buf_size = range_size * k_size_row;
@@ -1818,7 +1816,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
             const uint64_t v_size_row = ggml_row_size(v->type, n_embd_v_gqa);
             io.write(&v_size_row, sizeof(v_size_row));
 
-            // Read each range of cells of v_size length each into tmp_buf and write out
+            // Read each range of cells of v_size length and write out
             for (const auto & range : cr.data) {
                 const size_t range_size = range.second - range.first;
                 const size_t buf_size = range_size * v_size_row;
@@ -1852,7 +1850,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
 
             // For each row, we get the element values of each cell
             for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
-                // Read each range of cells of v_size_el length each into tmp_buf and write out
+                // Read each range of cells of v_size_el length and write out
                 for (const auto & range : cr.data) {
                     const size_t range_size = range.second - range.first;
                     const size_t src_offset = (range.first + j * kv_size) * v_size_el;
diff --git a/src/llama-memory-recurrent.cpp b/src/llama-memory-recurrent.cpp
index b88e57c43..ea815c587 100644
--- a/src/llama-memory-recurrent.cpp
+++ b/src/llama-memory-recurrent.cpp
@@ -785,8 +785,6 @@ void llama_memory_recurrent::state_write_data(llama_io_write_i & io, const std::
     io.write(&s_trans, sizeof(s_trans));
     io.write(&n_layer,   sizeof(n_layer));
 
-    std::vector<uint8_t> tmp_buf;
-
     // Iterate and write all the keys first, each row is a cell
     // Get whole range at a time
     for (uint32_t il = 0; il < n_layer; ++il) {
@@ -801,7 +799,7 @@ void llama_memory_recurrent::state_write_data(llama_io_write_i & io, const std::
         const uint64_t r_size_row = ggml_row_size(r_l[il]->type, hparams.n_embd_r());
         io.write(&r_size_row, sizeof(r_size_row));
 
-        // Read each range of cells of k_size length each into tmp_buf and write out
+        // Read each range of cells of k_size length and write out
         for (const auto & range : cell_ranges) {
             const size_t range_size = range.second - range.first;
             const size_t buf_size = range_size * r_size_row;
@@ -822,7 +820,7 @@ void llama_memory_recurrent::state_write_data(llama_io_write_i & io, const std::
             const uint64_t s_size_row = ggml_row_size(s_l[il]->type, hparams.n_embd_s());
             io.write(&s_size_row, sizeof(s_size_row));
 
-            // Read each range of cells of s_size length each into tmp_buf and write out
+            // Read each range of cells of s_size length and write out
             for (const auto & range : cell_ranges) {
                 const size_t range_size = range.second - range.first;
                 const size_t buf_size = range_size * s_size_row;
@@ -851,7 +849,7 @@ void llama_memory_recurrent::state_write_data(llama_io_write_i & io, const std::
 
             // For each row, we get the element values of each cell
             for (uint32_t j = 0; j < n_embd_s; ++j) {
-                // Read each range of cells of v_size_el length each into tmp_buf and write out
+                // Read each range of cells of v_size_el length and write out
                 for (const auto & range : cell_ranges) {
                     const size_t range_size = range.second - range.first;
                     const size_t src_offset = (range.first + j * mem_size) * s_size_el;