llama-context : report graph inputs and input tensors during sched reserve (#26625)

* llama-context : report graph inputs and input tensors during sched reserve

- fix the tg (token generation) graph bs label to use n_seqs instead of a hardcoded 1
- report the number of graph inputs from llm_graph_result::inputs for both the pp and tg graphs
- report the number of input tensors (nodes and their src tensors flagged with GGML_TENSOR_FLAG_INPUT)
- log a warning when an input tensor has an op other than GGML_OP_NONE
- log a trace line for each input tensor and the nodes (name and op) that use it

Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731

* cont : count input tensors before reserving the sched

* wip

* llama-graph : name the unnamed graph input tensors

- name the kv-cache idxs input tensors (attn_inp_k_idxs, attn_inp_v_idxs)
- name the recurrent state copy idxs input tensor (rs_s_copy)
- report the input tensor shape in the sched_reserve trace

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* llama-context : rename "graph inputs" to "graph input objects"

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* llama-context : report the sched reserve graph stats on a single line

- print nodes, splits, input objects and input tensors in one line
- when the pp and tg graphs differ, print each value as 'pp / tg'
  and annotate the line with the batch sizes used for each graph

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* cont : pad logs

src/llama-graph.cpp

@@ -2451,6 +2451,7 @@ ggml_tensor * llm_graph_context::build_inp_pos() const {
 
     cur = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, (int64_t)n_tokens*hparams.n_pos_per_embd());
     ggml_set_input(cur);
+    cb(cur, "inp_pos", -1);
 
     res->add_input(std::move(inp));
 
@@ -2465,7 +2466,7 @@ ggml_tensor * llm_graph_context::build_inp_attn_scale() const {
     // this need to be 1x1xN for broadcasting
     cur = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, 1, 1, n_tokens);
     ggml_set_input(cur);
-    ggml_set_name(cur, "attn_scale");
+    cb(cur, "inp_attn_scale", -1);
 
     res->add_input(std::move(inp));
 
@@ -2487,6 +2488,7 @@ ggml_tensor * llm_graph_context::build_inp_out_ids() const {
 
     cur = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_outputs);
     ggml_set_input(cur);
+    ggml_set_name(cur, "out_ids");
 
     res->add_input(std::move(inp));
 
@@ -2500,6 +2502,7 @@ ggml_tensor * llm_graph_context::build_inp_mean() const {
 
     cur = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_tokens, ubatch.n_seqs_unq);
     ggml_set_input(cur);
+    ggml_set_name(cur, "mean");
 
     res->add_input(std::move(inp));
 
@@ -2513,6 +2516,7 @@ ggml_tensor * llm_graph_context::build_inp_cls() const {
 
     cur = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, ubatch.n_seqs_unq);
     ggml_set_input(cur);
+    ggml_set_name(cur, "cls");
 
     res->add_input(std::move(inp));
 
@@ -2537,6 +2541,7 @@ ggml_tensor * llm_graph_context::build_inp_cross_embd() const {
 
     cur = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, n_enc);
     ggml_set_input(cur);
+    ggml_set_name(cur, "cross_embd");
 
     res->add_input(std::move(inp));
 
@@ -2550,6 +2555,7 @@ ggml_tensor * llm_graph_context::build_inp_pos_bucket_enc() const {
 
     cur = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_tokens, n_tokens);
     ggml_set_input(cur);
+    ggml_set_name(cur, "pos_bucket_enc");
 
     res->add_input(std::move(inp));
 
@@ -2567,6 +2573,7 @@ ggml_tensor * llm_graph_context::build_inp_pos_bucket_dec() const {
 
     cur = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_kv, n_tokens);
     ggml_set_input(cur);
+    ggml_set_name(cur, "pos_bucket_dec");
 
     res->add_input(std::move(inp));
 
@@ -2735,6 +2742,7 @@ llm_graph_input_attn_no_cache * llm_graph_context::build_attn_inp_no_cache() con
     // note: there is no KV cache, so the number of KV values is equal to the number of tokens in the batch
     inp->self_kq_mask = ggml_new_tensor_4d(ctx0, type_mask, n_tokens, n_tokens, 1, 1);
     ggml_set_input(inp->self_kq_mask);
+    cb(inp->self_kq_mask, "self_kq_mask", -1);
 
     inp->self_kq_mask_cnv = inp->self_kq_mask;
 
@@ -3511,6 +3519,7 @@ static std::unique_ptr<llm_graph_input_rs> build_rs_inp_impl(
 
     inp->s_copy = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_rs);
     ggml_set_input(inp->s_copy);
+    ggml_set_name(inp->s_copy, "rs_s_copy");
 
     inp->s_copy_main  = ggml_view_1d(ctx0, inp->s_copy, n_seqs, 0);
     inp->s_copy_extra = ggml_view_1d(ctx0, inp->s_copy, n_rs - n_seqs, n_seqs * inp->s_copy->nb[0]);