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
tools/llama-bench/llama-bench.cpp
+40 -38
View File
@@ -429,45 +429,45 @@ static void print_usage(int /* argc */, char ** argv) {
}
printf("\n");
printf("test parameters:\n");
printf(" -m, --model <filename> (default: %s)\n", join(cmd_params_defaults.model, ",").c_str());
printf(" -hf, -hfr, --hf-repo <user>/<model>[:quant] Hugging Face model repository; quant is optional, case-insensitive\n");
printf(" default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist.\n");
printf(" example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M\n");
printf(" (default: unused)\n");
printf(" -hff, --hf-file <file> Hugging Face model file. If specified, it will override the quant in --hf-repo\n");
printf(" (default: unused)\n");
printf(" -hft, --hf-token <token> Hugging Face access token\n");
printf(" (default: value from HF_TOKEN environment variable)\n");
printf(" --offline Offline mode: forces use of cache, prevents network access\n");
printf(" (default: disabled)\n");
printf(" -p, --n-prompt <n> (default: %s)\n", join(cmd_params_defaults.n_prompt, ",").c_str());
printf(" -n, --n-gen <n> (default: %s)\n", join(cmd_params_defaults.n_gen, ",").c_str());
printf(" -pg <pp,tg> (default: %s)\n", join(transform_to_str(cmd_params_defaults.n_pg, pair_str), ",").c_str());
printf(" -d, --n-depth <n> (default: %s)\n", join(cmd_params_defaults.n_depth, ",").c_str());
printf(" -b, --batch-size <n> (default: %s)\n", join(cmd_params_defaults.n_batch, ",").c_str());
printf(" -ub, --ubatch-size <n> (default: %s)\n", join(cmd_params_defaults.n_ubatch, ",").c_str());
printf(" -ctk, --cache-type-k <t> (default: %s)\n", join(transform_to_str(cmd_params_defaults.type_k, ggml_type_name), ",").c_str());
printf(" -ctv, --cache-type-v <t> (default: %s)\n", join(transform_to_str(cmd_params_defaults.type_v, ggml_type_name), ",").c_str());
printf(" -t, --threads <n> (default: %s)\n", join(cmd_params_defaults.n_threads, ",").c_str());
printf(" -C, --cpu-mask <hex,hex> (default: %s)\n", join(cmd_params_defaults.cpu_mask, ",").c_str());
printf(" --cpu-strict <0|1> (default: %s)\n", join(cmd_params_defaults.cpu_strict, ",").c_str());
printf(" --poll <0...100> (default: %s)\n", join(cmd_params_defaults.poll, ",").c_str());
printf(" -ngl, --n-gpu-layers <n> (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
printf(" -ncmoe, --n-cpu-moe <n> (default: %s)\n", join(cmd_params_defaults.n_cpu_moe, ",").c_str());
printf(" -sm, --split-mode <none|layer|row|tensor> (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
printf(" -mg, --main-gpu <i> (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
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(" -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());
printf(" -ts, --tensor-split <ts0/ts1/..> (default: 0)\n");
printf(" -m, --model <filename> (default: %s)\n", join(cmd_params_defaults.model, ",").c_str());
printf(" -hf, -hfr, --hf-repo <user>/<model>[:quant] Hugging Face model repository; quant is optional, case-insensitive\n");
printf(" default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist.\n");
printf(" example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M\n");
printf(" (default: unused)\n");
printf(" -hff, --hf-file <file> Hugging Face model file. If specified, it will override the quant in --hf-repo\n");
printf(" (default: unused)\n");
printf(" -hft, --hf-token <token> Hugging Face access token\n");
printf(" (default: value from HF_TOKEN environment variable)\n");
printf(" --offline Offline mode: forces use of cache, prevents network access\n");
printf(" (default: disabled)\n");
printf(" -p, --n-prompt <n> (default: %s)\n", join(cmd_params_defaults.n_prompt, ",").c_str());
printf(" -n, --n-gen <n> (default: %s)\n", join(cmd_params_defaults.n_gen, ",").c_str());
printf(" -pg <pp,tg> (default: %s)\n", join(transform_to_str(cmd_params_defaults.n_pg, pair_str), ",").c_str());
printf(" -d, --n-depth <n> (default: %s)\n", join(cmd_params_defaults.n_depth, ",").c_str());
printf(" -b, --batch-size <n> (default: %s)\n", join(cmd_params_defaults.n_batch, ",").c_str());
printf(" -ub, --ubatch-size <n> (default: %s)\n", join(cmd_params_defaults.n_ubatch, ",").c_str());
printf(" -ctk, --cache-type-k <t> (default: %s)\n", join(transform_to_str(cmd_params_defaults.type_k, ggml_type_name), ",").c_str());
printf(" -ctv, --cache-type-v <t> (default: %s)\n", join(transform_to_str(cmd_params_defaults.type_v, ggml_type_name), ",").c_str());
printf(" -t, --threads <n> (default: %s)\n", join(cmd_params_defaults.n_threads, ",").c_str());
printf(" -C, --cpu-mask <hex,hex> (default: %s)\n", join(cmd_params_defaults.cpu_mask, ",").c_str());
printf(" --cpu-strict <0|1> (default: %s)\n", join(cmd_params_defaults.cpu_strict, ",").c_str());
printf(" --poll <0...100> (default: %s)\n", join(cmd_params_defaults.poll, ",").c_str());
printf(" -ngl, --n-gpu-layers <n> (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
printf(" -ncmoe, --n-cpu-moe <n> (default: %s)\n", join(cmd_params_defaults.n_cpu_moe, ",").c_str());
printf(" -sm, --split-mode <none|layer|row|tensor> (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
printf(" -mg, --main-gpu <i> (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
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|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());
printf(" -ts, --tensor-split <ts0/ts1/..> (default: 0)\n");
printf(" -ot --override-tensor <tensor name pattern>=<buffer type>;...\n");
printf(" (default: disabled)\n");
printf(" -nopo, --no-op-offload <0|1> (default: 0)\n");
printf(" --no-host <0|1> (default: %s)\n", join(cmd_params_defaults.no_host, ",").c_str());
printf(" (default: disabled)\n");
printf(" -nopo, --no-op-offload <0|1> (default: 0)\n");
printf(" --no-host <0|1> (default: %s)\n", join(cmd_params_defaults.no_host, ",").c_str());
printf("\n");
printf(
"Multiple values can be given for each parameter by separating them with ','\n"
@@ -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 {