mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-24 15:14:10 +00:00
Change fmoe to be on by default
This commit is contained in:
@@ -1008,8 +1008,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
||||
params.attn_max_batch = std::stoi(argv[i]);
|
||||
return true;
|
||||
}
|
||||
if (arg == "-fmoe" || arg == "--fused-moe") {
|
||||
params.fused_moe_up_gate = true;
|
||||
if (arg == "-no-fmoe" || arg == "--no-fused-moe") {
|
||||
params.fused_moe_up_gate = false;
|
||||
return true;
|
||||
}
|
||||
if (arg == "-ger" || arg == "--grouped-expert-routing") {
|
||||
@@ -1807,7 +1807,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
|
||||
options.push_back({ "*", "-fa, --flash-attn", "enable Flash Attention (default: %s)", params.flash_attn ? "enabled" : "disabled" });
|
||||
options.push_back({ "*", "-mla, --mla-use", "enable MLA (default: %d)", params.mla_attn });
|
||||
options.push_back({ "*", "-amb, --attention-max-batch", "max batch size for attention computations (default: %d)", params.attn_max_batch});
|
||||
options.push_back({ "*", "-fmoe, --fused-moe", "enable fused MoE (default: %s)", params.fused_moe_up_gate ? "enabled" : "disabled" });
|
||||
options.push_back({ "*", "-no-fmoe, --no-fused-moe", "disable fused MoE (default: %s)", params.fused_moe_up_gate ? "enabled" : "disabled" });
|
||||
options.push_back({ "*", "-ger, --grouped-expert-routing", "enable grouped expert routing (default: %s)", params.grouped_expert_routing ? "enabled" : "disabled" });
|
||||
options.push_back({ "*", "-no-fug, --no-fused-up-gate", "disaable fused up-gate (default: %s)", params.fused_up_gate ? "enabled" : "disabled" });
|
||||
options.push_back({ "*", "-no-mmad, --no-fused-mul-multiadd", "disaable fused mul-multi_add (default: %s)", params.fused_mmad? "enabled" : "disabled" });
|
||||
|
||||
Reference in New Issue
Block a user