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

remove: mul_mat_q in compare llama bench and usage

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-29 10:38:36 +01:00
parent 2e64897d2e
commit 36fed7af50
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -32,9 +32,9 @@ int main(int argc, char ** argv) {
gpt_params params; gpt_params params;
if (argc == 1 || argv[1][0] == '-') { if (argc == 1 || argv[1][0] == '-') {
printf("usage: %s MODEL_PATH [N_KV_MAX] [IS_PP_SHARED] [NGL] [MMQ] <PP> <TG> <PL>\n" , argv[0]); printf("usage: %s MODEL_PATH [N_KV_MAX] [IS_PP_SHARED] [NGL] <PP> <TG> <PL>\n" , argv[0]);
printf(" <PP>, <TG> and PL are comma-separated lists of numbers without spaces\n\n"); printf(" <PP>, <TG> and PL are comma-separated lists of numbers without spaces\n\n");
printf(" example: %s ggml-model-f16.gguf 2048 0 999 0 128,256,512 128,256 1,2,4,8,16,32\n\n", argv[0]); printf(" example: %s ggml-model-f16.gguf 2048 0 999 128,256,512 128,256 1,2,4,8,16,32\n\n", argv[0]);
return 1 ; return 1 ;
} }

2
scripts/compare-llama-bench.py
View file

@ -31,7 +31,7 @@ PRETTY_NAMES = {
"model_size": "Model Size [GiB]", "model_n_params": "Num. of Parameters", "model_size": "Model Size [GiB]", "model_n_params": "Num. of Parameters",
"n_batch": "Batch size", "n_threads": "Threads", "type_k": "K type", "type_v": "V type", "n_batch": "Batch size", "n_threads": "Threads", "type_k": "K type", "type_v": "V type",
"n_gpu_layers": "GPU layers", "main_gpu": "Main GPU", "no_kv_offload": "NKVO", "n_gpu_layers": "GPU layers", "main_gpu": "Main GPU", "no_kv_offload": "NKVO",
"mul_mat_q": "MMQ", "tensor_split": "Tensor split" "tensor_split": "Tensor split"
} }
DEFAULT_SHOW = ["model_type"] # Always show these properties by default. DEFAULT_SHOW = ["model_type"] # Always show these properties by default.