lora: count lora nodes in graph_max_nodes (#18469)

* lora: count lora nodes in graph_max_nodes * 3 nodes per weight * 4 nodes * keep track n_lora_nodes from llama_model * fix assert * rm redundant header * common: load adapters before context creation * use 6 nodes
2025-12-30 15:53:12 +01:00
parent c32fa21db8
commit cd78e57c3a
6 changed files with 46 additions and 23 deletions
@@ -475,6 +475,9 @@ struct llama_model {
    // for quantize-stats only
    std::vector<std::pair<std::string, struct ggml_tensor *>> tensors_by_name;

+    // for keeping track of extra nodes used by lora adapters
+    uint32_t n_lora_nodes = 0;
+
    int64_t t_load_us  = 0;
    int64_t t_start_us = 0;