spec: support qwen3.5 & 3.6 eagle3 draft

Author: ruixiang63

src/models/qwen35.cpp

@@ -156,6 +156,8 @@ llama_model_qwen35::graph::graph(const llama_model & model, const llm_graph_para
 
     // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass.
     for (int il = 0; il < n_layer; ++il) {
+        res->t_layer_inp[il] = inpL;
+
         ggml_tensor * inpSA = inpL;
 
         cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);

src/models/qwen35moe.cpp

@@ -179,6 +179,8 @@ llama_model_qwen35moe::graph::graph(const llama_model & model, const llm_graph_p
 
     // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass.
     for (int il = 0; il < n_layer; ++il) {
+        res->t_layer_inp[il] = inpL;
+
         ggml_tensor * inpSA = inpL;
 
         cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);

tools/server/server-context.cpp

@@ -2977,6 +2977,17 @@ struct server_context_impl {
 
                                     bool do_reset = it == slot.prompt.checkpoints.rend();
 
+                                    // eagle3 draft is one position behind the target due to deferred boundary), so it
+                                    // can't resume from a checkpoint restored on a recurrent/hybrid target; re-process fully instead.
+                                    const bool spec_eagle3 = std::find(params_base.speculative.types.begin(), params_base.speculative.types.end(),
+                                                                       COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3) != params_base.speculative.types.end();
+                                    if (!do_reset && spec_eagle3 &&
+                                            (ctx_tgt_seq_rm_type == COMMON_CONTEXT_SEQ_RM_TYPE_FULL ||
+                                             ctx_tgt_seq_rm_type == COMMON_CONTEXT_SEQ_RM_TYPE_RS)) {
+                                        SLT_WRN(slot, "%s", "eagle3 draft cannot resume from a recurrent/hybrid checkpoint, forcing full re-processing\n");
+                                        do_reset = true;
+                                    }
+
                                     if (!do_reset) {
                                         // restore the context checkpoint
                                         it->load_tgt(ctx_tgt,       slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);