LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues 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
common/arg.cpp
+8 -6
View File
@@ -2508,7 +2508,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
add_opt(common_arg(
{"--mlock"},
"DEPRECATED in favor of `--load-mode`: mmap + force system to keep model in RAM rather than swapping or compressing",
"DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing",
[](common_params & params) {
LOG_WRN("DEPRECATED: --mlock is deprecated. use --load-mode mlock instead\n");
params.load_mode = LLAMA_LOAD_MODE_MLOCK;
@@ -2537,13 +2537,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"model loading mode (default: mmap)\n"
"- none: no special loading mode\n"
"- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)\n"
"- mlock: mmap + force system to keep model in RAM rather than swapping or compressing\n"
"- mlock: force system to keep model in RAM rather than swapping or compressing\n"
"- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing\n"
"- dio: use DirectIO if available\n",
[](common_params & params, const std::string & value) {
/**/ if (value == "none") { params.load_mode = LLAMA_LOAD_MODE_NONE; }
else if (value == "mmap") { params.load_mode = LLAMA_LOAD_MODE_MMAP; }
else if (value == "mlock") { params.load_mode = LLAMA_LOAD_MODE_MLOCK; }
else if (value == "dio") { params.load_mode = LLAMA_LOAD_MODE_DIRECT_IO; }
/**/ if (value == "none") { params.load_mode = LLAMA_LOAD_MODE_NONE; }
else if (value == "mmap") { params.load_mode = LLAMA_LOAD_MODE_MMAP; }
else if (value == "mlock") { params.load_mode = LLAMA_LOAD_MODE_MLOCK; }
else if (value == "mmap+mlock") { params.load_mode = LLAMA_LOAD_MODE_MMAP_MLOCK; }
else if (value == "dio") { params.load_mode = LLAMA_LOAD_MODE_DIRECT_IO; }
else { throw std::invalid_argument("invalid value"); }
}
).set_env("LLAMA_ARG_LOAD_MODE"));