vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama-bench : update usage docs

Browse source
This commit is contained in:
Aarni Koskela 2024-09-03 10:12:53 +03:00
parent e03e6cd7d2
commit 17732711e7
2 changed files with 56 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/llama-bench/README.md
View file

@ -27,13 +27,17 @@ options:
-m, --model <filename> (default: models/7B/ggml-model-q4_0.gguf) -m, --model <filename> (default: models/7B/ggml-model-q4_0.gguf)
-p, --n-prompt <n> (default: 512) -p, --n-prompt <n> (default: 512)
-n, --n-gen <n> (default: 128) -n, --n-gen <n> (default: 128)
-pg <pp,tg> (default: 512,128) -pg <pp,tg> (default: )
-b, --batch-size <n> (default: 2048) -b, --batch-size <n> (default: 2048)
-ub, --ubatch-size <n> (default: 512) -ub, --ubatch-size <n> (default: 512)
-ctk, --cache-type-k <t> (default: f16) -ctk, --cache-type-k <t> (default: f16)
-ctv, --cache-type-v <t> (default: f16) -ctv, --cache-type-v <t> (default: f16)
-t, --threads <n> (default: 16) -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) -ngl, --n-gpu-layers <n> (default: 99)
-rpc, --rpc <rpc_servers> (default: )
-sm, --split-mode <none|layer|row> (default: layer) -sm, --split-mode <none|layer|row> (default: layer)
-mg, --main-gpu <i> (default: 0) -mg, --main-gpu <i> (default: 0)
-nkvo, --no-kv-offload <0|1> (default: 0) -nkvo, --no-kv-offload <0|1> (default: 0)
@ -43,7 +47,10 @@ options:
-embd, --embeddings <0|1> (default: 0) -embd, --embeddings <0|1> (default: 0)
-ts, --tensor-split <ts0/ts1/..> (default: 0) -ts, --tensor-split <ts0/ts1/..> (default: 0)
-r, --repetitions <n> (default: 5) -r, --repetitions <n> (default: 5)
-o, --output <csv|json|md|sql> (default: md) --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) -v, --verbose (default: 0)
Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times. Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times.

4
examples/llama-bench/llama-bench.cpp
View file

@ -311,8 +311,8 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" -r, --repetitions <n> (default: %d)\n", cmd_params_defaults.reps); 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(" --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(" --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(" -o, --output <csv|json|jsonl|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(" -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(" -v, --verbose (default: %s)\n", cmd_params_defaults.verbose ? "1" : "0");
printf("\n"); printf("\n");
printf("Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times.\n"); printf("Multiple values can be given for each parameter by separating them with ',' or by specifying the parameter multiple times.\n");