sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama: end-to-end tests (#19802)

Browse Source 
* tests: add end-to-end tests per model architecture

* fixup for rebase

* fix use-after-free in llama-model-loader.cpp

* fix CI

* fix WebGPU

* fix CI

* disable CI for macOS-latest-cmake-arm64

* use expert_weights_scale only if != 0.0f

* comments
This commit is contained in:
Johannes Gäßler
2026-03-08 12:30:21 +01:00
committed by GitHub
parent a95047979a
commit a976ff081b
33 changed files with 1607 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
include/llama.h
View File

@@ -5,6 +5,7 @@
#include "ggml-cpu.h"
#include "ggml-backend.h"
#include "ggml-opt.h"
#include "gguf.h"
#include <stddef.h>
#include <stdint.h>
@@ -440,19 +441,30 @@ extern "C" {
LLAMA_API void llama_detach_threadpool(struct llama_context * ctx);
typedef void (*llama_model_set_tensor_data_t)(struct ggml_tensor * tensor, void * userdata);
// Create a new model from GGUF metadata as well as a function to set the tensor data
// - tensors are created as GGML_TYPE_F32 by default,
// override by adding a tensor with the same name but a different name to the context
LLAMA_API struct llama_model * llama_model_init_from_user(
struct gguf_context * metadata,
llama_model_set_tensor_data_t set_tensor_data, // function to initialize tensor data with
void * set_tensor_data_ud, // userdata for function
struct llama_model_params params);
DEPRECATED(LLAMA_API struct llama_model * llama_load_model_from_file(
const char * path_model,
struct llama_model_params params),
"use llama_model_load_from_file instead");
// Load the model from a file
// Load a 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)
// Load a 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,