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

* 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>

common/arg.cpp

@@ -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;
@@ -2537,12 +2537,14 @@ 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 == "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"); }
         }

include/llama.h

@@ -205,8 +205,9 @@ extern "C" {
     enum llama_load_mode {
         LLAMA_LOAD_MODE_NONE       = 0, // no special loading mode
         LLAMA_LOAD_MODE_MMAP       = 1, // memory map the model
-        LLAMA_LOAD_MODE_MLOCK     = 2, // mmap + force system to keep model in RAM rather than swapping or compressing
+        LLAMA_LOAD_MODE_MLOCK      = 2, // force system to keep model in RAM rather than swapping or compressing
-        LLAMA_LOAD_MODE_DIRECT_IO = 3, // use direct I/O if available
+        LLAMA_LOAD_MODE_MMAP_MLOCK = 3, // mmap + force system to keep model in RAM rather than swapping or compressing
+        LLAMA_LOAD_MODE_DIRECT_IO  = 4, // use direct I/O if available
     };
 
     LLAMA_API const char * llama_load_mode_name(enum llama_load_mode load_mode);

src/llama-model-loader.cpp

@@ -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

@@ -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

@@ -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";
     }
@@ -64,6 +66,7 @@ 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, "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);
 }

tests/test-arg-parser.cpp

@@ -143,6 +143,10 @@ static void test(void) {
     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", "mmap+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_MMAP_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);
@@ -187,6 +191,11 @@ static void test(void) {
     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", "mmap+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_MMAP_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));

tools/cli/README.md

@@ -55,10 +55,10 @@
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
 | `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
-| `--mlock` | DEPRECATED in favor of `--load-mode`: mmap + force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
+| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
-| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
+| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: force system to keep model in RAM rather than swapping or compressing<br/>- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
 | `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
 | `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
 | `--list-devices` | print list of available devices and exit |

tools/completion/README.md

@@ -138,10 +138,10 @@ llama-completion.exe -m models\gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
 | `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
-| `--mlock` | DEPRECATED in favor of `--load-mode`: mmap + force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
+| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
-| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
+| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: force system to keep model in RAM rather than swapping or compressing<br/>- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
 | `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
 | `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
 | `--list-devices` | print list of available devices and exit |

tools/llama-bench/llama-bench.cpp

@@ -459,7 +459,7 @@ static void print_usage(int /* argc */, char ** argv) {
     printf("  -nkvo, --no-kv-offload <0|1>                      (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
     printf("  -fa, --flash-attn <on|off|auto>                   (default: %s)\n", join(transform_to_str(cmd_params_defaults.flash_attn, llama_flash_attn_type_name), ",").c_str());
     printf("  -dev, --device <dev0/dev1/...>                    (default: auto)\n");
-    printf("  -lm, --load-mode <none|mmap|mlock|dio>      (default: %s)\n", join(transform_to_str(cmd_params_defaults.load_mode, llama_load_mode_name), ",").c_str());
+    printf("  -lm, --load-mode <none|mmap|mlock|mmap+mlock|dio> (default: %s)\n", join(transform_to_str(cmd_params_defaults.load_mode, llama_load_mode_name), ",").c_str());
     printf("  -mmp, --mmap <0|1>                                (DEPRECATED IN FAVOUR OF --load-mode)\n");
     printf("  -dio, --direct-io <0|1>                           (DEPRECATED IN FAVOUR OF --load-mode)\n");
     printf("  -embd, --embeddings <0|1>                         (default: %s)\n", join(cmd_params_defaults.embeddings, ",").c_str());
@@ -785,6 +785,8 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
                         mode = LLAMA_LOAD_MODE_MMAP;
                     } else if (m == "mlock") {
                         mode = LLAMA_LOAD_MODE_MLOCK;
+                    } else if (m == "mmap+mlock") {
+                        mode = LLAMA_LOAD_MODE_MMAP_MLOCK;
                     } else if (m == "dio") {
                         mode = LLAMA_LOAD_MODE_DIRECT_IO;
                     } else {

tools/server/README.md

@@ -72,10 +72,10 @@ For the full list of features, please refer to [server's changelog](https://gith
 | `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
-| `--mlock` | DEPRECATED in favor of `--load-mode`: mmap + force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
+| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
-| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
+| `-lm, --load-mode MODE` | model loading mode (default: mmap)<br/>- none: no special loading mode<br/>- mmap: memory-map model (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>- mlock: force system to keep model in RAM rather than swapping or compressing<br/>- mmap+mlock: mmap + force system to keep model in RAM rather than swapping or compressing<br/>- dio: use DirectIO if available<br/><br/>(env: LLAMA_ARG_LOAD_MODE) |
 | `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
 | `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
 | `--list-devices` | print list of available devices and exit |