llama-bench : update usage docs
This commit is contained in:
Aarni Koskela
parent
e03e6cd7d2
commit
17732711e7
2 changed files with 56 additions and 49 deletions
|
|
@ -24,27 +24,34 @@ usage: ./llama-bench [options]
|
|||
|
||||
options:
|
||||
-h, --help
|
||||
-m, --model <filename> (default: models/7B/ggml-model-q4_0.gguf)
|
||||
-p, --n-prompt <n> (default: 512)
|
||||
-n, --n-gen <n> (default: 128)
|
||||
-pg <pp,tg> (default: 512,128)
|
||||
-b, --batch-size <n> (default: 2048)
|
||||
-ub, --ubatch-size <n> (default: 512)
|
||||
-ctk, --cache-type-k <t> (default: f16)
|
||||
-ctv, --cache-type-v <t> (default: f16)
|
||||
-t, --threads <n> (default: 16)
|
||||
-ngl, --n-gpu-layers <n> (default: 99)
|
||||
-sm, --split-mode <none|layer|row> (default: layer)
|
||||
-mg, --main-gpu <i> (default: 0)
|
||||
-nkvo, --no-kv-offload <0|1> (default: 0)
|
||||
-fa, --flash-attn <0|1> (default: 0)
|
||||
-mmp, --mmap <0|1> (default: 1)
|
||||
--numa <distribute|isolate|numactl> (default: disabled)
|
||||
-embd, --embeddings <0|1> (default: 0)
|
||||
-ts, --tensor-split <ts0/ts1/..> (default: 0)
|
||||
-r, --repetitions <n> (default: 5)
|
||||
-o, --output <csv|json|md|sql> (default: md)
|
||||
-v, --verbose (default: 0)
|
||||
-m, --model <filename> (default: models/7B/ggml-model-q4_0.gguf)
|
||||
-p, --n-prompt <n> (default: 512)
|
||||
-n, --n-gen <n> (default: 128)
|
||||
-pg <pp,tg> (default: )
|
||||
-b, --batch-size <n> (default: 2048)
|
||||
-ub, --ubatch-size <n> (default: 512)
|
||||
-ctk, --cache-type-k <t> (default: f16)
|
||||
-ctv, --cache-type-v <t> (default: f16)
|
||||
-t, --threads <n> (default: 8)
|
||||
-C, --cpu-mask <hex,hex> (default: 0x0)
|
||||
--cpu-strict <0|1> (default: 0)
|
||||
--poll <0...100> (default: 50)
|
||||
-ngl, --n-gpu-layers <n> (default: 99)
|
||||
-rpc, --rpc <rpc_servers> (default: )
|
||||
-sm, --split-mode <none|layer|row> (default: layer)
|
||||
-mg, --main-gpu <i> (default: 0)
|
||||
-nkvo, --no-kv-offload <0|1> (default: 0)
|
||||
-fa, --flash-attn <0|1> (default: 0)
|
||||
-mmp, --mmap <0|1> (default: 1)
|
||||
--numa <distribute|isolate|numactl> (default: disabled)
|
||||
-embd, --embeddings <0|1> (default: 0)
|
||||
-ts, --tensor-split <ts0/ts1/..> (default: 0)
|
||||
-r, --repetitions <n> (default: 5)
|
||||
--prio <0|1|2|3> (default: 0)
|
||||
--delay <0...N> (seconds) (default: 0)
|
||||
-o, --output <csv|json|jsonl|md|sql> (default: md)
|
||||
-oe, --output-err <csv|json|jsonl|md|sql> (default: none)
|
||||
-v, --verbose (default: 0)
|
||||
|
||||
Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times.
|
||||
```
|
||||
|
|
|
|||
|
|
@ -286,34 +286,34 @@ static void print_usage(int /* argc */, char ** argv) {
|
|||
printf("\n");
|
||||
printf("options:\n");
|
||||
printf(" -h, --help\n");
|
||||
printf(" -m, --model <filename> (default: %s)\n", join(cmd_params_defaults.model, ",").c_str());
|
||||
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(" -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(" -rpc, --rpc <rpc_servers> (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
|
||||
printf(" -sm, --split-mode <none|layer|row> (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 <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str());
|
||||
printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str());
|
||||
printf(" --numa <distribute|isolate|numactl> (default: disabled)\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(" -r, --repetitions <n> (default: %d)\n", cmd_params_defaults.reps);
|
||||
printf(" --prio <0|1|2|3> (default: %d)\n", cmd_params_defaults.prio);
|
||||
printf(" --delay <0...N> (seconds) (default: %d)\n", cmd_params_defaults.delay);
|
||||
printf(" -o, --output <csv|json|md|sql> (default: %s)\n", output_format_str(cmd_params_defaults.output_format));
|
||||
printf(" -oe, --output-err <csv|json|md|sql> (default: %s)\n", output_format_str(cmd_params_defaults.output_format_stderr));
|
||||
printf(" -v, --verbose (default: %s)\n", cmd_params_defaults.verbose ? "1" : "0");
|
||||
printf(" -m, --model <filename> (default: %s)\n", join(cmd_params_defaults.model, ",").c_str());
|
||||
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(" -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(" -rpc, --rpc <rpc_servers> (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
|
||||
printf(" -sm, --split-mode <none|layer|row> (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 <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str());
|
||||
printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str());
|
||||
printf(" --numa <distribute|isolate|numactl> (default: disabled)\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(" -r, --repetitions <n> (default: %d)\n", cmd_params_defaults.reps);
|
||||
printf(" --prio <0|1|2|3> (default: %d)\n", cmd_params_defaults.prio);
|
||||
printf(" --delay <0...N> (seconds) (default: %d)\n", cmd_params_defaults.delay);
|
||||
printf(" -o, --output <csv|json|jsonl|md|sql> (default: %s)\n", output_format_str(cmd_params_defaults.output_format));
|
||||
printf(" -oe, --output-err <csv|json|jsonl|md|sql> (default: %s)\n", output_format_str(cmd_params_defaults.output_format_stderr));
|
||||
printf(" -v, --verbose (default: %s)\n", cmd_params_defaults.verbose ? "1" : "0");
|
||||
printf("\n");
|
||||
printf("Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times.\n");
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue