1 write to k_proj
Microsoft.ML.GenAI.Core (1)
Module\Attention.cs (1)
123this.k_proj = new QuantizedLinear(this._hiddenSize, this._numKeyValueHeads * this._headDim, hasBias: attentionBias, dtype: dtype);
2 references to k_proj
Microsoft.ML.GenAI.Core (2)
Module\Attention.cs (2)
152else if (this.q_proj is not null && this.k_proj is not null && this.v_proj is not null) 155keyStates = this.k_proj.forward(hiddenStates);