model: assert nextn_predict_layers to prevent underflow (#20783)

Address GHSA-645x-v54x-34w8.

When nextn_predict_layers >= n_layer, n_layer - nextn_predict_layers
can underflow (unsigned wrap), which corrupts n_layer_kv_from_start.

Assert nextn_predict_layers immediately after parsing the GGUF key.

Found-by: Pwno

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 85db938a7ad417eae39cfdb40c899ff34ef70918..06e0645352ed05ff3e69020fb7e199dfb7d468ad 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1673,6 +1673,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
 
                 // NextN/MTP parameters (GLM-OCR)
                 ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
+                GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
 
                 // TODO: when MTP is implemented, this should probably be updated if needed
                 hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -1706,6 +1707,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
 
                 // NextN/MTP parameters
                 ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS,        hparams.nextn_predict_layers, false);
+                GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
 
                 // TODO: when MTP is implemented, this should probably be updated if needed
                 hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -1752,6 +1754,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
 
                 // NextN/MTP parameters
                 ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS,        hparams.nextn_predict_layers, false);
+                GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
 
                 // TODO: when MTP is implemented, this should probably be updated if needed
                 hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
@@ -1926,6 +1929,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT,         hparams.n_layer_dense_lead, false);
 
                 ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS,              hparams.nextn_predict_layers, false);
+                GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
 
                 switch (hparams.n_layer) {
                     case 32: type = LLM_TYPE_30B_A3B; break;
@@ -2108,6 +2112,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM,               hparams.expert_weights_norm, false);
                 ml.get_key(LLM_KV_EXPERT_GATING_FUNC,                hparams.expert_gating_func);
                 ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS,              hparams.nextn_predict_layers, false);
+                GGML_ASSERT(hparams.nextn_predict_layers < hparams.n_layer && "nextn_predict_layers must be < n_layer");
 
                 // TODO: when MTP is implemented, this should probably be updated if needed
                 hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;