there is provided a method of generating a soft schedule for the transmission of data to a User Equipment. The method includes receiving traffic to be scheduled for transmission and generating a soft schedule for the transmission of the received data in accordance with a resource allocation and the received traffic. The method further includes transmitting the soft schedule to a scheduler in an underlying network slice, for transmission to the UE. There is also provided a scheduler including a processor and machine readable memory storing machine executable instructions which when executed by the processor configures the scheduler perform the above method.

A system and computer-implemented method include receiving a request for allocating graphical processing unit (GPU) resources for performing an operation. The request includes metadata identifying a client identifier (ID) associated with a client, throughput, and latency of the operation. A resource limit is determined for performing the operation based on the metadata. Attributes associated with each GPU resource of a plurality of GPU resources available for assignment are obtained. The attribute is analyzed that is associated with each GPU resource with respect to the resource limit. A set of GPU resources is identified from the plurality of GPU resources based on the analysis. A dedicated AI cluster is generated by patching the set of GPU resources within a single cluster. The dedicated AI cluster reserves a portion of a computation capacity of a computing system for a period of time and the dedicated AI cluster is allocated to the client associated with the client ID.

A system and computer-implemented method include accessing a request for allocating graphical processing unit (GPU) resources for performing an operation. The request includes metadata identifying a client identifier associated with a client, throughput, and a latency of the operation. A predicted resource limit for performing the operation is determined based on the metadata. A parameter of GPU resources is obtained. The parameter includes a status indicating whether a GPU resource is occupied for performing another operation. A GPU resource utilization value is determined for each node based on the status. The GPU resource utilization value indicates the amount of utilization of GPU resources of the corresponding node. The GPU resource utilization value of each node is compared with a pre-defined resource utilization threshold value. The GPU resources are re-scheduled based on the predicted resource limit. Further, a set of GPU resources from the re-scheduled GPU resources for performing the operation.

The present disclosure relates to secure deployment of model weights from a generative artificial intelligence (GenAI) platform to a cloud service. The method includes accessing the model metadata and a set of weights of a GenAI model associated with a GenAI platform. These model weights may be encrypted using a first encryption key that may be provided in the model metadata. These encrypted model weights may be decrypted based on the model metadata by utilizing the first encryption key from the model metadata. Each key may be associated with the specific type of GenAI model. Before storing the model weights from the GenAI platform cloud tenancy to a cloud storage in GenAI home region, the model weights may be encrypted again by utilizing a second encryption key. This encryption by the cloud may enable independent control over the sensitive information during transit and storing.

The present disclosure relates to resource allocation among a plurality of clients, for using a cloud-based service, e.g., a generative artificial intelligence (GenAI) service. A first target amount of resource and a second target amount of resource can be allocated to a first client and a second client (respectively). A first and a second client, a first target amount of resource can be allocated to a first client, and a second target amount of resource can be allocated to a second client for using the service. A request can be received from a third client for allocating resources; estimating that (i) the first client is using a first subset of the first target amount and not using a second subset of first target amount, and (ii) the second client is using a third subset of the second target amount and not using a fourth subset of second target amount. It can be determined that the second subset is greater than the fourth subset. At least a portion of the second subset can be allocated as a third target amount of resource to the third client.

DHCP methods adopted by a slave device connected to a host device are disclosed. The method includes: receiving a DHCP discover message from the host device; in response to the DHCP discover message, transmitting a DHCP offer message containing a DHCP renewal time configuration to the host device; receiving a DHCP request message from the host device; and in response to the DHCP request message, transmitting a DHCP acknowledgement message containing a client Internet Protocol (IP) address and the DHCP renewal time configuration to the host device.

A resource allocation device includes a slice request acquisition unit that receives a slice request including information indicating a request value range and a priority level for each of plural attributes of a slice; a request value selection unit that holds a request value selection policy table showing how to select a request value for each of the plural attributes from the request value range on the basis of the priority level and selects the request value for each of the plural attributes of the slice on the basis of request value selection policy indicated by the request value selection policy table; and a resource allocation unit that allocates a resource to the slice on the basis of the request value.

A controller includes a physical network information acquisition unit obtaining information about resource of a device and information about connection between devices in a wireless access network, a physical path calculation unit calculating physical path resource information based on the information about resource of the device and the information about connection between the devices, an abstract path resource calculation unit calculating abstract path resource information based on the physical path resource information, an abstract path correlation calculation unit generating correlation information between abstract paths, a resource pool storing the abstract path resource information and the correlation information, a temporary resource pool temporarily storing the abstract path resource information and the correlation information, an abstract resource allocation unit determining whether a slice meeting a requirement of a slice request can be generated, and a temporary resource calculation unit updating information in the temporary resource pool.

The present disclosure relates to secure deployment of model weights from a generative artificial intelligence (GenAI) platform to a cloud service. The method includes accessing the model metadata and a set of weights of a GenAI model associated with a GenAI platform. These model weights may be encrypted using a first encryption key that may be provided in the model metadata. These encrypted model weights may be decrypted based on the model metadata by utilizing the first encryption key from the model metadata. Each key may be associated with the specific type of GenAI model. Before storing the model weights from the GenAI platform cloud tenancy to a cloud storage in GenAI home region, the model weights may be encrypted again by utilizing a second encryption key. This encryption by the cloud may enable independent control over the sensitive information during transit and storing.