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

args: add -lm mlock where it mlocks but doesnt mmap (#26135)

Browse Source 
* arg: add `-lm mlock` where it mlocks but doesnt mmap

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* docs: rm unwanted docs changes

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* docs: revert auto-formatting

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* bench: fix automated review point 3

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* arg: revert the meaning of --mlock to non-mmap'ed mlock

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* docs: update docs

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* docs: remove extra changes from `llama-gen-docs`

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

---------

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2026-07-27 16:44:08 +08:00
committed by GitHub
parent d73c1d6b22
commit ad256ded30
10 changed files with 77 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+1 -1
View File
@@ -542,7 +542,7 @@ llama_model_loader::llama_model_loader(
tensor_buft_overrides = param_tensor_buft_overrides_p;
this->use_mmap = load_mode == LLAMA_LOAD_MODE_MMAP || load_mode == LLAMA_LOAD_MODE_MLOCK;
this->use_mmap = load_mode == LLAMA_LOAD_MODE_MMAP || load_mode == LLAMA_LOAD_MODE_MMAP_MLOCK;
this->use_direct_io = load_mode == LLAMA_LOAD_MODE_DIRECT_IO;
if (!fname.empty()) {
src/llama-model.cpp
+1 -1
View File
@@ -1249,7 +1249,7 @@ void llama_model_base::load_vocab(llama_model_loader & ml) {
bool llama_model_base::load_tensors(llama_model_loader & ml) {
const auto & split_mode = params.split_mode;
const bool use_mlock = params.load_mode == LLAMA_LOAD_MODE_MLOCK;
const bool use_mlock = params.load_mode == LLAMA_LOAD_MODE_MLOCK || params.load_mode == LLAMA_LOAD_MODE_MMAP_MLOCK;
const auto & tensor_split = params.tensor_split;
const int n_layer_all = hparams.n_layer_all;
src/llama.cpp
+7 -4
View File
@@ -54,6 +54,8 @@ const char * llama_load_mode_name(enum llama_load_mode load_mode) {
return "mmap";
case LLAMA_LOAD_MODE_MLOCK:
return "mlock";
case LLAMA_LOAD_MODE_MMAP_MLOCK:
return "mmap+mlock";
case LLAMA_LOAD_MODE_DIRECT_IO:
return "dio";
}
@@ -61,10 +63,11 @@ const char * llama_load_mode_name(enum llama_load_mode load_mode) {
}
enum llama_load_mode llama_load_mode_from_str(const char * str) {
if (std::strcmp(str, "none") == 0) { return LLAMA_LOAD_MODE_NONE; }
if (std::strcmp(str, "mmap") == 0) { return LLAMA_LOAD_MODE_MMAP; }
if (std::strcmp(str, "mlock") == 0) { return LLAMA_LOAD_MODE_MLOCK; }
if (std::strcmp(str, "dio") == 0) { return LLAMA_LOAD_MODE_DIRECT_IO; }
if (std::strcmp(str, "none") == 0) { return LLAMA_LOAD_MODE_NONE; }
if (std::strcmp(str, "mmap") == 0) { return LLAMA_LOAD_MODE_MMAP; }
if (std::strcmp(str, "mlock") == 0) { return LLAMA_LOAD_MODE_MLOCK; }
if (std::strcmp(str, "mmap+mlock") == 0) { return LLAMA_LOAD_MODE_MMAP_MLOCK; }
if (std::strcmp(str, "dio") == 0) { return LLAMA_LOAD_MODE_DIRECT_IO; }
throw std::invalid_argument(std::string("unknown load mode: ") + str);
}