Fused mul + multi_add op (#858)

* Adding fused mul+multi_add + CPU implementation

* fused mul+multi_add: CUDA

* fused mul+multi_add: command line argument to disable it

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

common/common.h

@@ -235,6 +235,7 @@ struct gpt_params {
     int  attn_max_batch    = 0;     // Max batch size to use when computing attention (only applicable if flash_attn = false)
     bool fused_moe_up_gate = false; // fused up*unary(gate) op for MoE models
     bool fused_up_gate     = true;  // fused up*unary(gate) op
+    bool fused_mmad        = true;  // fused mul+multi_add op
     bool grouped_expert_routing = false; // if to use grouped expert routing (BailingMoeV2 arch)
     int  min_experts       = -1;
     float thresh_experts   = 0;