nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Correct available split modes in llama-bench (#1539)

This commit is contained in:
Kawrakow 2026-03-28 09:28:01 +01:00 committed by GitHub
parent 93ae47e167
commit 798af8676a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/llama-bench/llama-bench.cpp
View File

@ -342,7 +342,7 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" -ngl, --n-gpu-layers <n> (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
printf(" --n-cpu-moe <n> (default: none)\n");
printf(" -rpc, --rpc <rpc_servers> (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
printf(" -sm, --split-mode <none|row|layer> (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
printf(" -sm, --split-mode <none|layer|graph>(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());