talk-llama : sync llama.cpp

This commit is contained in:
Georgi Gerganov
2025-02-03 22:42:26 +02:00
parent cff8868b5f
commit 3f91832352
17 changed files with 582 additions and 232 deletions

View File

@@ -323,8 +323,6 @@ struct llama_model {
// gguf metadata
std::unordered_map<std::string, std::string> gguf_kv;
std::vector<std::string> rpc_servers;
// list of devices used in this model
std::vector<ggml_backend_dev_t> devices;