upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

args: refactor mlock/mmap/directio into load-mode (#20834)

Browse Source 
* args: overhaul mmap/mlock/dio into single arg

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

* docs: update docs with llama-gen-docs

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

* chore: satisfy code quality

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

* args: make the `+` sign an actual modifier now

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

* chore: general code clean up + comments

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

* arg: fix deprecated flags support

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

* arg: quick sanity check

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

* bench: sync llama-bench argument parsing

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

* fix: bugfix variable behaviour + llama-bench lm column size

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

* arg: inverse commands should do the opposite instead of doing nothing

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

* bench: fix incorrect dash

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

* bench: fix missing modifiers for deprecated flags

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

* llama: switch back to thread_local

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

* arg: switch back to single enum

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

* docs: update arg docs

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

* chore: fix missing `mlock` from llama_load_mode_from_str + cleanup llama-bench

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

* llama: fix mlock not activating

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

* arg: add deprecation warning when old and new flags are combined

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

* arg: cont add comment for todo in the future

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

* docs: sync with upstream

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

* docs: re-sync with upstream again

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
2026-07-23 20:32:56 +08:00
committed by GitHub
parent da296d6e72
commit e6dd0e29a6
20 changed files with 315 additions and 207 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
tests/test-arg-parser.cpp
View File

@@ -1,6 +1,7 @@
#include "arg.h"
#include "common.h"
#include "download.h"
#include "llama.h"
#include <string>
#include <vector>
@@ -102,11 +103,9 @@ static void test(void) {
argv = {"binary_name", "--draft", "123"};
assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_EMBEDDING));
// negated arg
argv = {"binary_name", "--no-mmap"};
argv = {"binary_name", "-lm", "hello"};
assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
printf("test-arg-parser: test valid usage\n\n");
argv = {"binary_name", "-m", "model_file.gguf"};
@@ -132,6 +131,22 @@ static void test(void) {
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_SPECULATIVE));
assert(params.speculative.draft.n_max == 123);
argv = {"binary_name", "-lm", "none"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_NONE);
argv = {"binary_name", "-lm", "mmap"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_MMAP);
argv = {"binary_name", "-lm", "mlock"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_MLOCK);
argv = {"binary_name", "-lm", "dio"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_DIRECT_IO);
// multi-value args (CSV)
argv = {"binary_name", "--lora", "file1.gguf,\"file2,2.gguf\",\"file3\"\"3\"\".gguf\",file4\".gguf"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
@@ -158,13 +173,32 @@ static void test(void) {
assert(params.model.path == "blah.gguf");
assert(params.cpuparams.n_threads == 1010);
setenv("LLAMA_ARG_LOAD_MODE", "blah", true);
argv = {"binary_name"};
assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
setenv("LLAMA_ARG_LOAD_MODE", "mmap", true);
argv = {"binary_name"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_MMAP);
setenv("LLAMA_ARG_LOAD_MODE", "mlock", true);
argv = {"binary_name"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_MLOCK);
setenv("LLAMA_ARG_LOAD_MODE", "dio", true);
argv = {"binary_name"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.load_mode == LLAMA_LOAD_MODE_DIRECT_IO);
printf("test-arg-parser: test negated environment variables\n\n");
setenv("LLAMA_ARG_MMAP", "0", true);
setenv("LLAMA_ARG_LOAD_MODE", "none", true);
setenv("LLAMA_ARG_NO_PERF", "1", true); // legacy format
argv = {"binary_name"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.use_mmap == false);
assert(params.load_mode == LLAMA_LOAD_MODE_NONE);
assert(params.no_perf == true);
printf("test-arg-parser: test environment variables being overwritten\n\n");