Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

add --tensor-read-lazy

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-27 13:10:03 +02:00
parent e072597f9f
commit bb07e28f88
8 changed files with 37 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+8
View File
@@ -214,6 +214,12 @@ extern "C" {
LLAMA_API const char * llama_load_mode_name(enum llama_load_mode load_mode);
LLAMA_API enum llama_load_mode llama_load_mode_from_str(const char * str);
enum llama_tensor_read_lazy {
LLAMA_TENSOR_READ_LAZY_OFF = 0, // always read the whole tensor up front
LLAMA_TENSOR_READ_LAZY_AUTO = 1, // lazy only for marked tensors larger than 4 GiB (requires mmap)
LLAMA_TENSOR_READ_LAZY_ON = 2, // read the rows of tensors marked by the arch on demand (requires mmap)
};
enum llama_context_type {
LLAMA_CONTEXT_TYPE_DEFAULT = 0,
LLAMA_CONTEXT_TYPE_MTP = 1,
@@ -315,6 +321,8 @@ extern "C" {
enum llama_split_mode split_mode; // how to split the model across multiple GPUs
enum llama_load_mode load_mode; // how to load the model
enum llama_tensor_read_lazy tensor_read_lazy; // on-demand reading of tensors marked by the arch
// the GPU that is used for the entire model when split_mode is LLAMA_SPLIT_MODE_NONE
int32_t main_gpu;