Turn on graph reuse by default

This commit is contained in:
Iwan Kawrakow
2025-12-27 07:22:46 +00:00
parent 2fe098e938
commit bf3ff8ec41
3 changed files with 7 additions and 2 deletions

View File

@@ -1251,6 +1251,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.graph_reuse = true;
return true;
}
if (arg == "-no-gr" || arg == "--no-graph-reuse") {
params.graph_reuse = false;
return true;
}
if (arg == "-ser" || arg == "--smart-expert-reduction") {
CHECK_ARG
auto values = string_split_pairs<int,float>(argv[i], ',');
@@ -2131,6 +2135,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", "-no-mmad, --no-fused-mul-multiadd", "disable fused mul-multi_add (default: %s)", params.fused_mmad? "enabled" : "disabled" });
//options.push_back({ "*", "-rcache, --rope-cache", "enable RoPE cache (default: %s)", params.rope_cache ? "enabled" : "disabled" });
options.push_back({ "*", "-gr, --graph-reuse", "enable graph reuse (default: %s)", params.graph_reuse ? "enabled" : "disabled" });
options.push_back({ "*", "-no-gr, --no-graph-reuse", "disable graph reuse (default: %s)", !params.graph_reuse ? "enabled" : "disabled" });
options.push_back({ "*", "-ser, --smart-expert-reduction", "experts reduction (default: %d,%g)", params.min_experts, params.thresh_experts});
options.push_back({ "*", "-mqkv, --merge-qkv,", "merge Q,K,V (default: %d)", params.merge_qkv});
options.push_back({ "*", "-khad, --k-cache-hadamard,", "Use Hadamard transform for K-cache (default: %d)", params.k_cache_hadamard});