Method update

autoregressive/models/gpt.py:177–185

(self, input_pos, k_val, v_val)

        self.register_buffer('v_cache', torch.zeros(cache_shape, dtype=dtype))

    def update(self, input_pos, k_val, v_val):
        # input_pos: [S], k_val: [B, H, S, D]
        assert input_pos.shape[0] == k_val.shape[2]
        k_out = self.k_cache
        v_out = self.v_cache
        k_out[:, :, input_pos] = k_val
        v_out[:, :, input_pos] = v_val

        return k_out, v_out


class Attention(nn.Module):