diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp
index 16d42c4ae3..acc13b0bee 100644
--- a/src/llama-graph.cpp
+++ b/src/llama-graph.cpp
@@ -533,113 +533,6 @@ bool llm_graph_input_mem_hybrid::can_reuse(const llm_graph_params & params) {
     return res;
 }
 
-void llm_graph_input_mem_hybrid_iswa::set_input(const llama_ubatch * ubatch) {
-    const auto * attn_ctx = mctx->get_attn();
-
-    // base tensors may not be allocated if there are no non-SWA attention layers
-    if (inp_attn->self_k_idxs && inp_attn->self_k_idxs->buffer) {
-        attn_ctx->get_base()->set_input_k_idxs(inp_attn->self_k_idxs, ubatch);
-        attn_ctx->get_base()->set_input_v_idxs(inp_attn->self_v_idxs, ubatch);
-
-        attn_ctx->get_base()->set_input_kq_mask(inp_attn->self_kq_mask, ubatch, cparams.causal_attn);
-    }
-
-    // swa tensors may not be allocated if there are no SWA attention layers
-    if (inp_attn->self_k_idxs_swa && inp_attn->self_k_idxs_swa->buffer) {
-        attn_ctx->get_swa()->set_input_k_idxs(inp_attn->self_k_idxs_swa, ubatch);
-        attn_ctx->get_swa()->set_input_v_idxs(inp_attn->self_v_idxs_swa, ubatch);
-
-        attn_ctx->get_swa()->set_input_kq_mask(inp_attn->self_kq_mask_swa, ubatch, cparams.causal_attn);
-    }
-
-    const int64_t n_rs = mctx->get_recr()->get_n_rs();
-
-    if (inp_rs->s_copy) {
-        GGML_ASSERT(ggml_backend_buffer_is_host(inp_rs->s_copy->buffer));
-        int32_t * data = (int32_t *) inp_rs->s_copy->data;
-
-        // assuming copy destinations ALWAYS happen ONLY on the cells between head and head+n
-        for (uint32_t i = 0; i < n_rs; ++i) {
-            data[i] = mctx->get_recr()->s_copy(i);
-        }
-    }
-}
-
-bool llm_graph_input_mem_hybrid_iswa::can_reuse(const llm_graph_params & params) {
-    const auto * mctx = static_cast<const llama_memory_hybrid_iswa_context *>(params.mctx);
-
-    this->mctx = mctx;
-
-    bool res = true;
-
-    const auto * attn_ctx = mctx->get_attn();
-
-    // base tensors may not be allocated if there are no non-SWA attention layers
-    if (inp_attn->self_k_idxs && inp_attn->self_k_idxs->buffer) {
-        res &= inp_attn->self_k_idxs->ne[0] == params.ubatch.n_tokens;
-      //res &= inp_attn->self_v_idxs->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
-
-        res &= inp_attn->self_kq_mask->ne[0] == attn_ctx->get_base()->get_n_kv();
-        res &= inp_attn->self_kq_mask->ne[1] == params.ubatch.n_tokens;
-    }
-
-    // swa tensors may not be allocated if there are no SWA attention layers
-    if (inp_attn->self_k_idxs_swa && inp_attn->self_k_idxs_swa->buffer) {
-        res &= inp_attn->self_k_idxs_swa->ne[0] == params.ubatch.n_tokens;
-      //res &= inp_attn->self_v_idxs_swa->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
-
-        res &= inp_attn->self_kq_mask_swa->ne[0] == attn_ctx->get_swa()->get_n_kv();
-        res &= inp_attn->self_kq_mask_swa->ne[1] == params.ubatch.n_tokens;
-    }
-
-    res &= inp_rs->s_copy->ne[0] == mctx->get_recr()->get_n_rs();
-
-    res &= inp_rs->s_copy_main->ne[0]  == params.ubatch.n_seqs;
-    res &= inp_rs->s_copy_extra->ne[0] == mctx->get_recr()->get_n_rs() - params.ubatch.n_seqs;
-
-    res &= inp_rs->head == mctx->get_recr()->get_head();
-    res &= inp_rs->rs_z == mctx->get_recr()->get_rs_z();
-
-    return res;
-}
-
-void llm_graph_input_sampling::set_input(const llama_ubatch * ubatch) {
-    // set the inputs only for the active samplers in the current ubatch
-    std::unordered_set<llama_seq_id> active_samplers;
-    for (uint32_t i = 0; i < ubatch->n_tokens; i++) {
-        if (ubatch->output[i]) {
-            llama_seq_id seq_id = ubatch->seq_id[i][0];
-            active_samplers.insert(seq_id);
-        }
-    }
-
-    for (auto seq_id : active_samplers) {
-        if (samplers.find(seq_id) == samplers.end()) {
-            continue;
-        }
-
-        auto & sampler = samplers[seq_id];
-
-        if (sampler->iface->backend_set_input) {
-            sampler->iface->backend_set_input(sampler);
-        }
-    }
-}
-
-bool llm_graph_input_sampling::can_reuse(const llm_graph_params & params) {
-    if (samplers.size() != params.samplers.size()) {
-        return false;
-    }
-
-    for (const auto & [seq_id, sampler] : params.samplers) {
-        if (samplers[seq_id] != sampler) {
-            return false;
-        }
-    }
-
-    return true;
-}
-
 //
 // llm_graph_result
 //