ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : add option to override model tensor buffers (#11397)

Browse source 
* llama : add option to override tensor buffers

* ggml : fix possible underflow in ggml_nbytes
This commit is contained in:
Diego Devesa 2025-04-02 14:52:01 +02:00 • committed by GitHub
parent a10b36c91a
commit e0e912f49b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 108 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

1
common/common.h
View file

@ -279,6 +279,7 @@ struct common_params {
std::vector<std::string> in_files; // all input files
std::vector<std::string> antiprompt; // strings upon which more user input is prompted (a.k.a. reverse prompts)
std::vector<llama_model_kv_override> kv_overrides;
std::vector<llama_model_tensor_buft_override> tensor_buft_overrides;
bool lora_init_without_apply = false; // only load lora to memory, but do not apply it to ctx (user can manually apply lora later using llama_adapter_lora_apply)
std::vector<common_adapter_lora_info> lora_adapters; // lora adapter path with user defined scale