Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bench: add --tensor-read-lazy (#27881)

Browse Source 
* bench: add --tensor-read-lazy

* rm the alias

* rename to LLAMA_LAZY_MODE_*
This commit is contained in:
Xuan-Son Nguyen
2026-08-28 20:51:05 +02:00
committed by GitHub
parent 6fe7498016
commit 50f068ffff
10 changed files with 78 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+5 -5
View File
@@ -214,10 +214,10 @@ 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_lazy_mode {
LLAMA_LAZY_MODE_OFF = 0, // always read the whole tensor up front
LLAMA_LAZY_MODE_AUTO = 1, // lazy only for marked tensors larger than 4 GiB (requires mmap)
LLAMA_LAZY_MODE_ON = 2, // read the rows of tensors marked by the arch on demand (requires mmap)
};
enum llama_context_type {
@@ -321,7 +321,7 @@ 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
enum llama_lazy_mode lazy_mode; // 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;