CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases 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
12 changed files with 108 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama-model-loader.cpp
View File

@@ -445,7 +445,8 @@ llama_model_loader::llama_model_loader(
std::vector<std::string> & splits,
bool use_mmap,
bool check_tensors,
const struct llama_model_kv_override * param_overrides_p) {
const llama_model_kv_override * param_overrides_p,
const llama_model_tensor_buft_override * param_tensor_buft_overrides_p) {
int trace = 0;
if (getenv("LLAMA_TRACE")) {
trace = atoi(getenv("LLAMA_TRACE"));
@@ -457,6 +458,8 @@ llama_model_loader::llama_model_loader(
}
}
tensor_buft_overrides = param_tensor_buft_overrides_p;
// Load the main GGUF
struct ggml_context * ctx = NULL;
struct gguf_init_params params = {