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

llama : add llama_model_load_from_splits (#11255)

Browse source 
* llama : add `llama_model_load_from_splits`

* update
This commit is contained in:
Xuan Son Nguyen 2025-01-16 13:54:08 +01:00 • committed by GitHub
parent c67cc9837d
commit 681149ced2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 116 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

10
include/llama.h
View file

@ -418,10 +418,20 @@ extern "C" {
struct llama_model_params params),
"use llama_model_load_from_file instead");
// Load the model from a file
// If the file is split into multiple parts, the file name must follow this pattern: <name>-%05d-of-%05d.gguf
// If the split file name does not follow this pattern, use llama_model_load_from_splits
LLAMA_API struct llama_model * llama_model_load_from_file(
const char * path_model,
struct llama_model_params params);
// Load the model from multiple splits (support custom naming scheme)
// The paths must be in the correct order
LLAMA_API struct llama_model * llama_model_load_from_splits(
const char ** paths,
size_t n_paths,
struct llama_model_params params);
DEPRECATED(LLAMA_API void llama_free_model(struct llama_model * model),
"use llama_model_free instead");