graph : fix KQ mask, lora, cvec reuse checks (#19644)

* graph : fix KQ mask reuse condition

* cont : dedup KQ mask build and can_reuse

* cont : fix build

* graph : fix adapter check for reuse
This commit is contained in:
Georgi Gerganov
2026-02-16 09:21:11 +02:00
committed by GitHub
parent 267ba5a1d9
commit d5dfc33027
4 changed files with 67 additions and 54 deletions
+3
View File
@@ -39,6 +39,8 @@ private:
std::vector<ggml_tensor *> tensors; // per layer
};
using llama_adapter_cvec_ptr = std::shared_ptr<llama_adapter_cvec>;
//
// llama_adapter_lora
//
@@ -84,3 +86,4 @@ struct llama_adapter_lora {
};
using llama_adapter_loras = std::unordered_map<llama_adapter_lora *, float>;
using llama_adapter_loras_ptr = std::unique_ptr<llama_adapter_loras>;