model : add control vector support where missing (#20653)

* Add control vector functions to qwen3.5 and qwen-next models

* Add missing cvec compatibility to the rest of the models

* Adjust comments and formatting

* cleanup

* whitespace

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

src/models/bitnet.cpp

@@ -121,6 +121,9 @@ llm_build_bitnet::llm_build_bitnet(const llama_model & model, const llm_graph_pa
         cur = ggml_add(ctx0, cur, ffn_inp);
         cb(cur, "l_out", il);
 
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
         // input for next layer
         inpL = cur;
     }

src/models/chatglm.cpp

@@ -111,8 +111,13 @@ llm_build_chatglm::llm_build_chatglm(const llama_model & model, const llm_graph_
 
         }
 
-        inpL = ggml_add(ctx0, cur, ffn_inp);
+        cur = ggml_add(ctx0, cur, ffn_inp);
-        cb(inpL, "l_out", il);
+
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
+        // input for next layer
+        inpL = cur;
     }
 
     cur = build_norm(inpL,

src/models/cogvlm.cpp

@@ -86,6 +86,10 @@ llm_build_cogvlm::llm_build_cogvlm(const llama_model & model, const llm_graph_pa
         cur = ggml_add(ctx0, cur, ffn_inp);
         cb(cur, "ffn_out", il);
 
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
+        // input for next layer
         inpL = cur;
     }
 

src/models/eurobert.cpp

@@ -82,6 +82,7 @@ llm_build_eurobert::llm_build_eurobert(const llama_model & model, const llm_grap
 
         cur = ggml_add(ctx0, cur, ffn_inp);
 
+        // input for next layer
         inpL = cur;
     }
     cur = inpL;

src/models/jais.cpp

@@ -66,8 +66,14 @@ llm_build_jais::llm_build_jais(const llama_model & model, const llm_graph_params
                     LLM_FFN_SILU, LLM_FFN_PAR, il);
             cb(cur, "ffn_out", il);
         }
-        inpL = ggml_add(ctx0, cur, ffn_inp);
+
-        cb(inpL, "l_out", il);
+        cur = ggml_add(ctx0, cur, ffn_inp);
+
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
+        // input for next layer
+        inpL = cur;
     }
     cur = build_norm(inpL,
             model.output_norm,

src/models/kimi-linear.cpp

@@ -362,6 +362,7 @@ llm_build_kimi_linear::llm_build_kimi_linear(const llama_model & model, const ll
         cur = build_cvec(cur, il);
         cb(cur, "l_out", il);
 
+        // input for next layer
         inpL = cur;
     }
     cur = inpL;

src/models/lfm2.cpp

@@ -177,6 +177,9 @@ llm_build_lfm2<iswa>::llm_build_lfm2(const llama_model & model, const llm_graph_
         cb(ffn_norm_out, "model.layers.{}.ffn_out", il);
 
         cur = ggml_add(ctx0, cur, ffn_out);
+
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
     }
 
     cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);

src/models/plamo2.cpp

@@ -71,6 +71,7 @@ llm_build_plamo2::llm_build_plamo2(const llama_model & model, const llm_graph_pa
         cur = ggml_add(ctx0, cur, residual);
         cb(cur, "ffn_residual", il);
 
+        // input for next layer
         inpL = cur;
     }
 

src/models/plamo3.cpp

@@ -109,6 +109,8 @@ llm_build_plamo3<iswa>::llm_build_plamo3(const llama_model & model, const llm_gr
 
         cur = build_cvec(cur, il);
         cb(cur, "l_out", il);
+
+        // input for next layer
         inpL = cur;
     }
 

src/models/qwen35.cpp

@@ -64,6 +64,9 @@ llm_build_qwen35::llm_build_qwen35(const llama_model & model, const llm_graph_pa
         cur = ggml_add(ctx0, cur, ffn_residual);
         cb(cur, "post_ffn", il);
 
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
         // Input for next layer
         inpL = cur;
     }

src/models/qwen35moe.cpp

@@ -64,6 +64,9 @@ llm_build_qwen35moe::llm_build_qwen35moe(const llama_model & model, const llm_gr
         cur = ggml_add(ctx0, cur, ffn_residual);
         cb(cur, "post_moe", il);
 
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
         // Input for next layer
         inpL = cur;
     }

src/models/qwen3next.cpp

@@ -56,6 +56,9 @@ llm_build_qwen3next::llm_build_qwen3next(const llama_model & model, const llm_gr
         cur = ggml_add(ctx0, cur, ffn_residual);
         cb(cur, "post_moe", il);
 
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
         // Input for next layer
         inpL = cur;
     }

src/models/smallthinker.cpp

@@ -101,6 +101,7 @@ llm_build_smallthinker<iswa>::llm_build_smallthinker(const llama_model & model,
         cur = ffn_out;
 
         cur = ggml_add(ctx0, cur, ffn_inp);
+
         cur = build_cvec(cur, il);
         cb(cur, "l_out", il);
 

src/models/step35-iswa.cpp

@@ -145,9 +145,11 @@ llm_build_step35_iswa::llm_build_step35_iswa(const llama_model & model, const ll
             cb(cur, "ffn_out", il);
         }
         cur = ggml_add(ctx0, cur, ffn_inp);
+
         cur = build_cvec(cur, il);
         cb(cur, "l_out", il);
 
+        // input for next layer
         inpL = cur;
     }