Method, apparatus and computer program

Abstract

Typically, Channel State Information (CSI) comprises parameters associated with measurements performed by a UE, however CSI reports can comprise use of Artificial Intelligence (AI) / Machine learning (ML) for predicted measurements. These reports are of varying complexity due to different AI / ML models therefore there is a need to differentiate between CSI reports not associated with AI / ML processing to ensure reports are processed efficiently. The invention comprises reporting to a network entity information comprising a first number associated with artificial intelligence related CSI processing that is supported at the apparatus and a second number associated with CSI processing that is supported at the apparatus. A CSI report is generated at least partly on the information associated with the AI related CSI processing and provided to the network entity.

Description

Technical Field Various examples of this disclosure relate to methods, apparatuses, and computer programs for a communication network. Background A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network. A communication device may be provided with a service by an application server. Such communication networks operate in accordance with standards such as those provided by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of standards are the so-called 5G (5th Generation) standards provided by 3GPP. Summary Some examples of this disclosure will be described with respect to certain aspects. These aspects are not intended to indicate key or essential features of the embodiments of this disclosure, nor are they intended to be used to limit the scope of thereof. Other features, aspects, and elements will be readily apparent to a person skilled in the art in view of this disclosure. For example, it should be appreciated that further aspects may be provided by the combination of any two or more of the various aspects described below. According to an aspect, there is provided an apparatus comprising: means for reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus; means for generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and means for providing, to the network entity, the at least one CSI report. In some examples, the second number is associated with any type of CSI processing that is supported at the apparatus. In some examples, the second number is associated with a total of CSI processing that is supported at the apparatus. In some examples, the Al related CSI processing comprises ML-related CSI processing. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing is associated with all CSI processing supported at the apparatus. In some examples, the first number is reported within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the apparatus comprises: means for receiving, from the network entity, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the information that has been reported, wherein the at least one CSI report is generated based, at least partly, on the configuration. In some examples, the apparatus comprises: means for determining a maximum number of CSI reports that the apparatus is capable of processing within a first orthogonal frequency division multiplex, OFDM, symbol, wherein the determining is based on the information. In some examples, the means for determining the maximum number comprises: means for determining whether a number of calculations for CSI processing, at the apparatus within the first OFDM symbol, associated with an Al related CSI processing is less than or equal to the first number; means for determining whether a total number of calculations for CSI processing, at the apparatus within the first OFDM symbol, is less than or equal to the second number; and means for, in response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, generating the at least one CSI report. In some examples, a number of processing units, O_CPU , comprised within the apparatus that are available for processing the at least one CSI report associated with the Al related model has a first value, O_CPU=x , wherein the first value is dependent on a quantity being reported in the at least one CSI report. In some examples, the apparatus is one of: a communication device, a user equipment, or a terminal. According to an aspect, there is provided a method performed by an apparatus, the method comprising: reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus; generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and providing, to the network entity, the at least one CSI report. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing is associated with all CSI processing supported at the apparatus. In some examples, the first number is reported within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the method is further comprising: receiving, from the network entity, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the information that has been reported, wherein the at least one CSI report is generated based, at least partly, on the configuration. In some examples, the method is further comprising: determining a maximum number of CSI reports that the apparatus is capable of processing within a first orthogonal frequency division multiplex, OFDM, symbol, wherein the determining is based on the information. In some examples, the determining the maximum number comprises: determining whether a number of calculations for CSI processing, at the apparatus within the first OFDM symbol, associated with an Al related CSI processing is less than or equal to the first number; determining whether a total number of calculations for CSI processing, at the apparatus within the first OFDM symbol, is less than or equal to the second number; and in response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, generating the at least one CSI report. In some examples, a number of processing units, O_CPU , comprised within the apparatus that are available for processing the at least one CSI report associated with the Al related model has a first value, O_CPU=x , wherein the first value is dependent on a quantity being reported in the at least one CSI report. In some examples, the apparatus is one of: a communication device, a user equipment, or a terminal. According to an aspect, there is provided an apparatus comprising: circuitry configured to perform: reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus; circuitry configured to perform: generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and circuitry configured to perform: providing, to the network entity, the at least one CSI report. According to an aspect, there is provided an apparatus comprising: at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform: reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus; generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and providing, to the network entity, the at least one CSI report. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the apparatus. In some examples, the second number for CSI processing is associated with all CSI processing supported at the apparatus. In some examples, the first number is reported within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the apparatus is further caused to perform: receiving, from the network entity, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the information that has been reported, wherein the at least one CSI report is generated based, at least partly, on the configuration. In some examples, the apparatus is further caused to perform: determining a maximum number of CSI reports that the apparatus is capable of processing within a first orthogonal frequency division multiplex, OFDM, symbol, wherein the determining is based on the information. In some examples, the determining the maximum number comprises: determining whether a number of calculations for CSI processing, at the apparatus within the first OFDM symbol, associated with an Al related CSI processing is less than or equal to the first number; determining whether a total number of calculations for CSI processing, at the apparatus within the first OFDM symbol, is less than or equal to the second number; and in response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, generating the at least one CSI report. In some examples, a number of processing units, O_CPU , comprised within the apparatus that are available for processing the at least one CSI report associated with the Al related model has a first value, O_CPU=x , wherein the first value is dependent on a quantity being reported in the at least one CSI report. In some examples, the apparatus is one of: a communication device, a user equipment, or a terminal. According to an aspect, there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform at least the following: reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus; generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and providing, to the network entity, the at least one CSI report. According to an aspect, there is provided an apparatus comprising: means for receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device; means for providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; and means for receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. In some examples, the apparatus is further comprising: means for determining the configuration for CSI reporting based, at least partly, on the information that has been received, wherein the configuration is associated with the Al related CSI processing. In some examples, the second number is associated with any type of CSI processing that is supported at the communication device. In some examples, the second number is associated with a total of CSI processing that is supported at the communication device. In some examples, the Al related CSI processing comprises ML-related CSI processing. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing is associated with all CSI processing supported at the communication device. In some examples, the first number is received within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the apparatus is a network entity. For example, the network entity is a gNodeB. According to an aspect, there is provided a method performed by an apparatus, the method comprising: receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device; providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; and receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. In some examples, the method further comprises: determining the configuration for CSI reporting based, at least partly, on the information that has been received, wherein the configuration is associated with the Al related CSI processing. In some examples, the second number is associated with any type of CSI processing that is supported at the communication device. In some examples, the second number is associated with a total of CSI processing that is supported at the communication device. In some examples, the Al related CSI processing comprises ML-related CSI processing. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing is associated with all CSI processing supported at the communication device. In some examples, the first number is received within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the apparatus is a network entity. For example, the network entity is a gNodeB. According to an aspect, there is provided an apparatus comprising: circuitry configured to perform: receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device; circuitry configured to perform: providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; and circuitry configured to perform: receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. According to an aspect, there is provided an apparatus comprising: at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform: receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device; providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; and receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. In some examples, the apparatus is further caused to perform: determining the configuration for CSI reporting based, at least partly, on the information that has been received, wherein the configuration is associated with the Al related CSI processing. In some examples, the second number is associated with any type of CSI processing that is supported at the communication device. In some examples, the second number is associated with a total of CSI processing that is supported at the communication device. In some examples, the Al related CSI processing comprises ML-related CSI processing. In some examples, the first number for CSI processing comprises: a number, N_(CPU,ML) , of CSI calculations, for Al related CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing comprises: a number, N_CPU , of CSI calculations, for CSI processing, that are supported by the communication device. In some examples, the second number for CSI processing is associated with all CSI processing supported at the communication device. In some examples, the first number is received within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers. In some examples, the apparatus is a network entity. For example, the network entity is a gNodeB. According to an aspect, there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform at least the following: receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device; providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; and receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. A computer product stored on a medium may cause an apparatus to perform the methods as described herein. A non-transitory computer readable medium comprising program instructions, that, when executed by an apparatus, cause the apparatus to perform the methods as described herein. An electronic device may comprise apparatus as described herein. Various other aspects and further embodiments are also described in the following detailed description and in the attached claims. According to some aspects, there is provided the subject matter of the independent claims. Some further aspects are defined in the dependent claims. The embodiments that do not fall under the scope of the claims are to be interpreted as examples useful for understanding the disclosure. List of Abbreviations: AF: Application Function Al: Artificial intelligence AMF: Access and Mobility Management Function AN: Access Network BM: Beam management BS: Base Station CC: Component carrier CN: Core Network CSI: Channel state information CPU: CSI processing unit CRI: CSI reference signal resource indicator DL: Downlink eNB: eNodeB FLOPs: Floating point operations per second gNB: gNodeB lloT: Industrial Internet of Things LCM: Life cycle management LTE: Long Term Evolution NEF: Network Exposure Function NG-RAN: Next Generation Radio Access Network NF: Network Function NR: New Radio NRF: Network Repository Function NW: Network MS: Mobile Station ML: Machine learning OFDM: Orthogonal frequency division multiplexing PCF Policy Control Function PLMN: Public Land Mobile Network RAN: Radio Access Network RF: Radio Frequency RS: Reference signal RSRP: Reference signal received power SMF: Session Management Function SI NR: Signal to inference plus noise ratio PU: Processing unit UE: User Equipment UDR: Unified Data Repository UDM: Unified Data Management UL: Uplink UPF: User Plane Function 3GPP: 3rd Generation Partnership Project 5G: 5th Generation 5GC: 5G Core network 5G-AN: 5G Radio Access Network 5GS: 5G System Brief Description of Drawings Some examples will now be described, by way of illustrative and non-limiting example only, with reference to the accompanying drawings in which: FIG. 1 shows a schematic representation of a 5G communication system; FIG. 2 shows a schematic representation of an apparatus for the 5G communication system of FIG. 1; FIG. 3 shows a schematic representation of a communication device; FIG. 4 shows a graphical representation of a complexity of AI / ML models from evaluation results in terms of floating point operations per second (FLOPs) and number of parameters for beam management (BM) cases; FIG. 5 shows an example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting; FIG. 6 shows another example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting; FIG. 7 shows another example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting; FIG. 8 shows an example method flow diagram performed by an apparatus; FIG. 9 shows another example method flow diagram performed by an apparatus; and FIG. 10 shows a schematic representation of a non-volatile memory medium storing instructions which when executed by a processor allow a processor to perform one or more of the steps of the method of FIGS. 8 to 9. Detailed Description Channel state information (CSI) parameters are quantities related to the state of a channel. Communication devices, such as user equipments (UEs), report CSI parameters to a network (e.g., to a base station) as feedback. The CSI parameters may be provided as feedback in a CSI report. Examples of CSI parameters include: Channel Quality Information (CQI), Precoding Matrix Indicator (PMI), CSI reference signal resource indicator (CRI), synchronisation signal / physical broadcast channel resource block indicator (SSBRI), Layer Indicator (LI), Rank Indicator (RI), layer 1 reference signal received power (L1-RSRP). A communication device (e.g., a UE) may receive CSI reference signals from a network (e.g., a base station) to be used in order to measure CSI feedback. Upon receiving a CSI report comprising CSI parameters from the communication device, the network schedules downlink data transmissions to the communication devices accordingly. The CSI reporting framework is comprised of two parts, including a part for configuration and a part for triggering. ‘CSI-ResourceConfig’ specifies what type of reference signal is to be transmitted. ‘CSI-ResourceConfig’ also configures the types of the transmission (e.g., periodic, aperiodic, semipersistent). In this manner, ‘CSI-ResourceConfig’ triggers the transmission of resources. ‘CSI-ReportConfig’ specifies which of ‘CSI-ResourceConfig’ is to be used for the measurements. ‘CSI-ReportConfig’ comprises a number of parameters including: ‘reportConfigType’, ‘reportQuantity’, ‘reportFreqConfiguration’, ‘timeRestrictionForChannelMeasurements’, ‘timeRestrictionForlnterferenceMeasurements’, and ‘codebookConfig’. For example, the ‘reportConfigType’ parameter indicates the scheduling method of the report. Examples of scheduling methods include: periodic, aperiodic and semi. Furthermore, the ‘reportQuantity’ parameter indicates what to measure. A type of quantities to measure may be grouped into CSI-related quantities, or L1-RSRP-related quantities. CSI reference signals (CSI-RSs) are used for beamforming support. CSI-RS may be configured by layer 3 to be either beam-specific or device / UE-specific. CSI-RS are mapped onto certain resources in the frequency and time domain. These reference signals are used for performing tasks such as beam acquisition and evaluation, adaptation of the beam (e.g., beam refinement), decision making for beam switching, and UE tracking with steerable beams. Typically, CSI reports have comprised parameters that are associated with measurements performed by the UE (e.g., beam measurements). However, with the ever growing use of Artificial Intelligence (AI)ZMachine Learning (ML) features being used in communication networks, some CSI reports may comprise predicted measurements. 3GPP Release-18 started a study on artificial intelligence (Al) / machine learning (ML) for the New Radio (NR) Air Interface, wherein the objectives are described in RP-213599. In this study item, there are objective to explore the benefits of augmenting the air interface with features enabling improved support of AI / ML-based algorithms for enhanced performance and / or reduced complexity / overhead. Several use cases are considered to enable the identification of a common AI / ML framework, including functional requirements of AI / ML architecture, which could be used in subsequent projects. The study also identifies areas where AI / ML could improve the performance of air-interface functions. In this context, ‘AI / ML model’ may be interpreted as a model associated with Al, or a model associated with ML. Alternatively, an ‘AI / ML model’ may be a model associated with both Al and ML processing. In order to distinguish AI / ML models and functionalities supported by the AI / ML models, RAN1 #111 introduced two different ML-related identification types (‘functionality identification’, and ‘model identification’), where the model identification was assumed to use a “model-ID” in the identification process and functionality identification was assumed to use a “functionality” in the identification process. For AI / ML enhancements related to beam management, two sub-use cases have been identified in RAN1 including: beam prediction in the spatial domain (‘BM-Case1’) and beam prediction in the time (including spatial and time) domain (‘BM-Case2’). A motivation of such AI / ML enhancements is to support a reduced overhead and lower beam measurements and reporting latency. Details of model inference (e.g., related to beam reporting) have been previously discussed in RAN1 meetings. Based on the agreements, at least predicted beams are to be reported by UEs, and the reporting of predicted L1-RSRP may also take place. For both ‘BM-CaseT and ‘BM-Case2’, it is expected that the CSI reporting framework is applicable as the functionality framework. 3GPP RAN #102 meeting approved the Rel-19 work item (Wl) on AI / ML for NR Air Interface (e.g., RP-234039), based on AI / ML techniques to New Radio (NR) air interface has been studied in FS_NR_AIML_Air. In the following disclosure, there are examples that are related to enhancements to AI / ML for beam management, and are related to one or more of the following 3GPP objectives, as follows: Objectives in RP-234039 include: AI / ML general framework for one-sided AI / ML models within the realm of what has been studied in the FS_NR_AIML_Air project: - Signalling and protocol aspects of Life Cycle Management (LCM) enabling functionality and model (if justified) selection, activation, deactivation, switching, fallback - Identification related signalling is part of the above objective. - Necessary signalling / mechanism(s) for LCM to facilitate model training, inference, performance monitoring, data collection (except for the purpose of core network (CN) / operations administration maintenance (OAM) / over-the-top (OTT) collection of UE-sided model training data) for both UE-sided and NW-sided models - Signalling mechanism of applicable functionalities / models Beam management. DL Tx beam prediction for both UE-sided model and NW-sided model, encompassing [RAN1 / RAN2]: - Spatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams (“BM-Case1”) - Temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams (“BM-Case2”) - Specify necessary signalling / mechanism(s) to facilitate LCM operations specific to the Beam Management use cases, if any. - Enabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE. Study objectives with corresponding checkpoints in RAN#105 (Sept ’24): - Necessity and details of model Identification concept and procedure in the context of LCM [RAN2 / RAN1] - CN / OAM / OTT collection of UE-sided model training data [RAN2 / RAN1]: - For the FS_NR_AIML_Air study use cases, identify the corresponding contents of UE data collection - Analyse the UE data collection mechanisms identified during the FS_NR_AIML_Air (TR 38.843 section 7.2.1.3.2) study along with the implications and limitations of each of the methods. - Model transfer / delivery [RAN2 / RAN1]: - Determine whether there is a need to consider standardised solutions for transferring / delivering AI / ML model(s) considering at least the solutions identified during the FS_NR_AIML_Air study For AI / ML enhancements related to beam management, two sub-use cases have been identified in 3GPP RAN1. This includes beam prediction in the spatial domain (BM-Case1) and beam prediction in the time domain (BM-Case2). A motivation is to support a reduced overhead and lower beam measurements and reporting latency. In the past 3GPP RAN1 meetings, there were a number of agreements related to the AI / ML for BM, with some being copied below. Agreement 1: For AI / ML-based beam management, support BM-Case1 and BM-Case2 for characterization and baseline performance evaluations. BM-Case1: Spatial-domain DL beam prediction for Set A of beams based on measurement results of Set B of beams. BM-Case2: Temporal DL beam prediction for Set A of beams based on the historic measurement results of Set B of beams. Agreement 2: For the sub use case BM-Case1 and BM-Case2, further study the following alternatives for the predicted beams: Alternative (alt.) 1: DL Tx beam prediction - Alt.2: DL Rx beam prediction - Alt.3: Beam pair prediction (a beam pair consists of a DL Tx beam and a corresponding DL Rx beam) Agreement 3: In order to facilitate the AI / ML model inference, study the following aspects as a starting point: Enhanced or new configurations / UE reporting / UE measurement, e.g., Enhanced or new beam measurement and / or beam reporting Enhanced or new signalling for measurement configuration / triggering - Signalling of assistance information (if applicable) Other aspect(s) is not precluded Agreement 4: For BM-Case2 with a UE-side AI / ML model, study the potential specification impact of L1 signalling to report the following information of AI / ML model inference to NW: - The beam(s) of N future time instance(s) that is based on the output of AI / ML model inference - For further study (FFS): value of N - FFS: Predicted L1-RSRP corresponding to the beam(s) - Information about the timestamp corresponding the reported beam(s) - FFS: explicit or implicit - FFS: other information Agreement 5: For BM-Case1 and BM-Case2 with a network-side AI / ML model, study potential specification impacton the following L1 reporting enhancement for AI / ML model inference: UE to report the measurement results of more than 4 beams in one reporting instance Other L1 reporting enhancements can be considered Agreement 6: For BM-Case2, study necessity, benefit(s) and potential specification impact from the following additional aspects for Al model inference: - Reporting information about measurements of multiple past time instances in one reporting instance for BM-Case2 - Note: only applicable to network-side AI / ML model - Note: The potential performance gains of measurement reporting should be justified by considering UCI payload overhead Agreement 7: For BM-Case1 and BM-Case2, study necessity, benefit(s) and potential specification impact from the following additional aspects for Al model inference: - How to perform beam indication of beams in Set A not in Set B - Note: the legacy mechanism may be sufficient Agreement 8: For BM-Case1 and BM-Case2 with a UE-side AI / ML model, study potential specification impact of Al model inference from the following additional aspects on top of previous agreements: Indication of the associated Set A from network to UE, e.g., association / mapping of beams within Set A and beams within Set B if applicable Beam indication from network for UE reception Note: The second bullet may or may not have additional specification impact (e.g., legacy mechanism may be reused). Observation 1: At least for BM-Case1 with a UE-side AI / ML model, for Al model inference, the legacy transmission configuration indicator (TCI) state mechanism may be used to perform beam indication of beams. As discussed above, details of AI / ML model inference (e.g., related to beam measurements, reporting, and beam indication) were discussed for BM-Case1 and BM-Case2. Beam prediction models have different levels of complexity levels and 3GPP TR 38.843 captures some investigations related to that. FIG. 4 and Table 1 illustrate model parameter and computational complexity in floating point operations per second (FLOPs) for BM-Case 1 and BM-Case 2, Tx beam prediction and beam pair prediction respectively, according to the reported assumption in BM_Table 1 and BM_Table2. It is noted that optimization of AI / ML model (e.g., in terms of model / computational complexity) was not discussed in the study. Model complexity in number of model parameters Model complexity in number of model size Computational complexity (FLOPs) BM-Case 1 DLTx beam More than 1k to 4.9M majority reported less than 1M or about 1M 50Kbytes to 20M bytes majority reported less than 0.1 Mbytes ~ 0.6M bytes ~2.7Kto 222M majority reported less than 1M or 10s M BM-Case 1 DL beam pair 72k to 4.9M majority reported less than 0.1s M ~ 1M 0.17Mbytes to 21 Mbytes majority reported less than 1 Mbytes ~ 4Mbytes 15Kto 224M majority reported less than 1M ~ 4 M BM-Case 2 DLTx beam 35k to 11M majority reported less than 0.1 s M ~ 1M 0.5M bytes to 15M bytes majority reported about 1s Mbytes ~90K to 54M majority reported less than 0.1s M or 1s M BM-Case 2 DL beam pair 20k to 13M majority reported about 0.1 M~1M 0.08M to 15M majority reported about 1 Mbytes ~90K to 443M majority reported less than 0.4 M or 1s M Table 1: AI / ML model complexity / computation complexity used in the evaluations for AI / ML in beam management. FIG. 4 shows a graphical representation of a complexity of AI / ML models from evaluation results in terms of floating point operations per second (FLOPs) and number of parameters for beam management (BM) cases. FIG. 4 is a graphical representation associated with Table 1 shown above. In FIG. 4 there are data points associated with one of four cases (i.e., each row from Table 1). There is a first set 401 of data points that are associated with a BM-Case 1 DL Tx beam. There is a second set 403 of data points that are associated with a BM-Case 1 DL beam pair. There is a third set 405 of data points that are associated with a BM-Case 2 DL Tx beam. There is a fourth set 407 of data points that are associated with a BM-Case 2 DL beam pair. On the x-axis 409 is the number of model parameters (e.g., M value). On the y-axis 411 is the computational complexity, measured in FLOPs. In this context, the model may be an AI / ML model. As seen in FIG. 4, in general, the computational complexity will be higher with the larger number of model parameters. This means that more processing power will be consumed at a communication device in order to process a CSI report, and / or the processing may take longer, when the number of model parameters is higher. It may be seen in FIG. 4 that AI / ML models, used by the UE, may be associated with different complexities (e.g., with differing numbers of parameters). One AI / ML model may be different from another AI / ML model and that may lead to a different use of a UE's hardware for AI / ML model inference. Unlike traditional CSI processing, a higher complexity may be associated with the AI / ML-based CSI processing. Furthermore, unlike traditional CSI processing whereby a fixed complexity may be assumed at the UE, the AI / ML-based CSI processing may be subject to varying complexities due to AI / ML models (e.g., models may be updated / changed due to one of a number of reasons even when the models are supporting the same functionality). Therefore, there may be a need to differentiate between CSI reports that are associated with AI / ML CSI processing and CSI reports that are not associated with AI / ML CSI processing, in order to ensure CSI reports (AI / ML and non-AI / ML) are processed efficiently. When a CSI report is processed at a communication device (e.g., a UE), at least one processing unit (e.g., central processing unit) of the communication device is utilised. The communication device will perform processing for the CSI report whether it is associated with an AI / ML model or not. However, the communication device will have hardware limitations on the amount of processing units to be used for CSI processing. Furthermore, it may be that the communication device has other limits on processing units that may be used, or a number of calculations per second that may be performed at the communication device. Information related to CSI processing units (CPUs) and CSI processing criteria is provided in 3GPP TS 38.214, in Section 5.2.1.6 and Section 5.4. In 3GPP TS 38.214 it is stated that: The UE indicates the number of supported simultaneous CSI calculations NCPU with parameter simultaneousCSI-ReportsPerCC in a component carrier, and simultaneousCSI-ReportsAIICC across all component carriers. If a UE supports NCPU simultaneous CSI calculations it is said to have NCPU CSI processing units for processing CSI reports. If L CPUs are occupied for calculation of CSI reports in a given OFDM symbol, the UE has NCPU - i unoccupied CPUs. If N CSI reports start occupying their respective CPUs on the same OFDM symbol on which NCPU - L CPUs are unoccupied, where each CSI report n = 0,..., N - 1 corresponds to 0^, the UE is not required to update the N - M requested CSI reports with lowest priority (according to Clause 5.2.5), where 0 <M <N is the largest value such that o <NCPU - L holds. A UE is not expected to be configured with an aperiodic CSI trigger state containing more than Ncpu Reporting Settings. Processing of a CSI report occupies a number of CPUs for a number of symbols as follows: - °cpu = 0 for a CSI report with CSI-ReportConfig with higher layer parameter reportQuantity set to 'none' and CSI-RS-ResourceSet with higher layer parameter trs-Info configured - °cpu = 1 for a CSI report with CSI-ReportConfig with higher layer parameter reportQuantity set to 'cri-RSRP', 'ssb-lndex-RSRP', 'cri-SINR', 'ssb-lndex-SINR', 'cri- RSRP- Index', 'ssb-lndex-RSRP- Index', 'cri-SINR- Index', 'ssb-lndex-SINR- Index ' or 'none' (and CSI-RS-ResourceSet with higher layer parameter trs-lnfo not configured) - OCPU = (Y + 1) ■ X, for a CSI report with CSI-ReportConfig with higher layer parameter reportQuantity set to 'tdcp' and with number of delays Y configured by higher layer parameter Y. where the value of X 6 {1,2} / s reported by UE capability. - for a CSI report with CSI-ReportConfig with higher layer parameter reportQuantity set to 'cri-RI-PMI-CQI', 'cri-RI-i1', 'cri-RI-U-CQI', 'cri-RI-CQI', or 'cri-RI-LI-PMI-CQI', - if max{ppdcch, Pcsi-rs, Pul} s 3, and if a CSI report is aperiodically triggered without transmitting a PUSCH with either transport block or HARQ-ACK or both when L = 0 CPUs are occupied, where the CSI corresponds to a single CSI with wideband frequency-granularity and to at most 4 CSI-RS ports in a single resource without CRI report and where codebookType is set to 'typel-SinglePanel' or where reportQuantity is set to 'cri-RI-CQI', OCPU = NCPU, - if a CSI-ReportConfig is configured with codebookType set to 'typel-SinglePanel' and the corresponding CSI-RS Resource Set for channel measurement is configured with two Resource Groups and N Resource Pairs, OCPU = X ■ N + M, where X is the number of CPUs occupied by a pair of CMRs subject to mTRP-CSI-numCPU-r17 and M is defined in clause 5.2.1.4.2, - if a CSI-ReportConfig contains a list of L sub-configurations provided by the higher layer parameter [csi-ReportSubConfigList], - °cpu = Si=i K) f°r periodic CSI reporting, where Ki is the total number of CSI-RS resources corresponding to the i-th sub-configuration. - °cpu = K) for aperiodic and semi-persistent CSI reporting, where Kj is the total number of CSI-RS resources corresponding to the i-th sub-configuration, and where the i-th sub-configuration is from N indicated sub-configurations out of L sub-configurations contained in a CSI-ReportConfig, where N <L and N >1. - if a CSI-ReportConfig is configured with the higher layer parameter reportQuantity set to 'cri-RI-PMI-CQI', codebookType set to 'typell-CJT-r18' or 'typell-CJT-PortSelection-r18' and the corresponding NZP-CSI-RS-ResourceSet for channel measurement is configured with 1 <NTRP <4 resources, OCPU = X ■ NTRP, where X e {1,1.5,2} is reported by UE capability indication, - if a CSI-ReportConfig is configured with the higher layer parameter reportQuantity set to 'cri-RI-PMI-CQI' and with codebookType set to 'typell-Doppler-r18' or 'typell-Doppler-PortSelection-r18', - if the corresponding CSI-RS Resource Set for channel measurement is aperiodic and configured with K CSI-RS resources, OCPU = Y1-K, where Y^e {2 / 3,1,2,3} / s reported by UE capability indication, - if the corresponding CSI-RS Resource Set for channel measurement is periodic or semi-persistent and configured with a single CSI-RS resource, 0CPU = 4 for N4 = 1 and 0CPU = Y2 ■ N4 >4, for N4 >1. where the value of N4 is configured by the higher layer parameter N4, and Y2 e {2 / 3,1,2,3} / s reported by UE capability indication, - otherwise, OCPU = Ks, where Ks is the number of CSI-RS resources in the CSI-RS resource set for channel measurement. NR CSI reporting framework defined in Release 15 (Rel-15) has undergone various changes over later releases while maintaining the core components as in the Rel-15 framework. For example, 3GPP TS 38.214 defines how a UE shall use CSI processing units (CPUs) for CSI reporting. A CSI processing unit is a processing unit for CSI processing. The number of CSI processing units may be defined differently considering various contexts (e.g., periodic / semi-persistent / aperiodic, multiple transmission and reception point (mTRP) / coherent joint transmission (CJT), CSI-RS ports, etc..) and considering CSI quantities (e.g., CSI reference signal resource indicator (cri), precoding matrix indicator (PMI), rank indicator (RI)) of the CSI report. A CSI processing unit (CPU) may be considered to be a processing unit (of a communication device) suitable for processing and / or generating a CSI report. For an AI / ML-enabled features such as beam prediction, CSI compression, and CSI prediction, it is expected that AI / ML functionality (or functionalities) may refer to CSI reporting configuration(s). However, how the AI / ML functionalities may change or impact the determination of CSI processing units appears to be undefined. AI / ML functionality is often associated with ML models, which are either visible to the network, or not visible to the NW, depending on whether the model identification is supported or not. In general, UEs use hardware (e.g., AI / ML hardware accelerators) where there are limitations on the number of AI / ML models they run across different AI / ML-enabled features. Such limitations also depend on the exact AI / ML models active or used at a given time when supporting an AI / ML functionality. It is not defined how hardware limitations at a UE are impacting determination of CSI processing units for CSI reporting when there are CSI reports associated with active AI / ML functionalities. It should be understood that the terms ‘AI / ML-enabled’, ‘AI / ML-related’, ‘AI / ML-based’ may be used interchangeably in the following examples. AI / ML may mean at least one of: Al or ML (also written as Al and / or ML). One or more of the following examples aims to address one or more of the issues discussed above. One or more of the following examples are related to enhancing existing CSI processing framework so to manage the CSI computational capability while enabling AI / ML features (e.g., beam prediction). In examples, there is method performed by an apparatus (e.g., a communication device, UE, etc), wherein the method comprises reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus. The method also comprises generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al-related CSI processing, and providing, to the network entity, the at least one CSI report. In examples, there is a method performed by an apparatus (e.g., communication device, UE, terminal, etc.), wherein the method comprises reporting, to a network entity, information related to a first number for channel state information, CSI, processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus. The method further comprises determining a number of processing units of the apparatus to use for processing a CSI report, wherein the determining is based on the information, and wherein the CSI report is associated with the Al-related CSI processing. The method further comprises generating, based on the determining, the CSI report utilising at least one processing unit, and providing, to the base station, the CSI report. In this manner, one or more of the examples show how a UE may determine a number of CSI processing units for an AI / ML-enabled CSI report (e.g., for AI / ML-enabled beam prediction at the UE). Furthermore, how to enable flexibility, at a UE, to change a number of CSI processing units for an AI / ML-enabled CSI report, for example, when an applicable AI / ML model associated with the CSI report / CSI configuration is changed. These examples, and others, will be described in more detail below, alongside FIGS. 5 to 10. Before explaining the examples in greater detail, an example communication device (as shown in FIG. 3) that is capable of processing and transmitting CSI reports will be described. The communication device is part of a communication system (as shown in FIG. 1). The communication device is able to communicate with one or more of the entities of the communication system (as shown in FIG. 1) via an apparatus (as shown in FIG. 2), which may be part of / comprised in a network entity such as a base station. Network entities, such as base stations, and communication devices may communicate with each other, such that the communication device is able to provide CSI reports to the network. Certain general aspects of the communication system and the communication device are briefly explained with reference to FIGS. 1 to 3 to assist in understanding the technology underlying the described examples. FIG. 1 shows a schematic representation of a 5G communication system 100. The wireless communication system 100 comprises one more communication devices 102 such as user equipments (UEs), or terminals. The wireless communication system 100 comprises a 5G system (5GS). The 5GS comprises a 5G radio access network (5G-RAN) 106, a 5G core network (5GC) 104 comprising one or more network functions (NF), one or more application functions (AFs) 108, and one or more data networks (DNs) 110. The 5G-RAN 106 may comprise one or more gNodeB (gNB) distributed unit (DU) functions connected to one or more gNodeB (gNB) centralized unit (CU) functions. The 5GC 104 comprises an access and mobility management function (AMF) 112, a session management function (SMF) 114, an authentication server function (AUSF) 116, a user data management (UDM) 118, a user plane function (UPF) 120, a network exposure function (NEF) 122 and / or other NFs. Some of the examples as shown below may be applicable to 3GPP 5G standards. However, some examples may also be applicable to 5G-advanced, 4G, 3G and other 3GPP standards. In a wireless communication system 100, such as that shown in FIG. 1, communication devices 102, such as for example, terminals, user apparatuses, user equipments (UE), and / or machine-type communication devices are provided with wireless access via at least one base station or similar wireless transmitting and / or receiving node or point. The communication device 102 is provided with an appropriate signal receiving and transmitting apparatus for enabling communications, for example enabling access to a communication network or communications directly with other devices. The communication device 102 may access a carrier provided by a base station or access point, and transmit and / or receive communications on the carrier. FIG. 2 illustrates an example of an apparatus 200. The apparatus 200 may be for the 5G communication system of FIG. 1. The apparatus 200 may be for controlling a function of one or more network entities and / or network functions, such as the entities of the 5G-RAN or the 5GC as illustrated on FIG. 1. The apparatus 200 comprises at least one random access memory (RAM) 211a, at least one read only memory (ROM) 211b, at least one processor 212, 213 and an input / output interface 214. The at least one processor 212, 213 is coupled to the RAM 211a and the ROM 211b. The at least one processor 212, 213 may be configured to execute an appropriate software code 215. The software code 215 may for example allow to perform one or more steps to perform one or more of the present aspects or examples. The software code 215 may be stored in the ROM 211b. The apparatus 200 may be interconnected with another apparatus 200 controlling another entity / function of the 5G-AN or the 5GC. . In some examples, apparatus 200 may be configured to provide one or more functions of the 5G-AN or the 5GC. For example, apparatus 200 may be configured to perform at least some functionality of a particular function of the 5G-AN or the 5GC. For example, apparatus 200 may be configured to operate as a particular function of the 5G-AN or the 5GC. In alternative examples, apparatus 200 may be configured to perform at least some functionality of two or more functions of the 5G-AN and / or the 5GC. For example, apparatus 200 may be configured to operate as two or more functions of the 5G-AN and / or the 5GC. The apparatus 200 may comprise one or more circuits, or circuitry (not shown) which may be configured to perform one or more of the present aspects or examples. FIG. 3 illustrates an example of a communication device 300. The communication device 300 may be similar to the communication device 102 illustrated in FIG. 1. The communication device 300 may be provided by any device capable of sending and receiving radio signals. Non-limiting examples of a communication device 300 are a user equipment, a terminal, a mobile station (MS) or mobile device such as a mobile phone or what is known as a ’smart phone’, a computer provided with a wireless interface card or other wireless interface facility (e.g., USB dongle), a personal data assistant (PDA) or a tablet provided with wireless communication capabilities, a machine-type communications (MTC) device, a Cellular Internet of things (CloT) device, or a terrestrial / maritime / aerial vehicle such as a car, a truck, a boat, an air plane, or a drone, or any combinations of these or the like. The communication device 300 may provide, for example, communication of data for carrying communications. The communications may be one or more of voice, electronic mail (email), text message, multimedia, data, machine data and so on. The communication device 300 may receive signals over an air or radio interface 307 via appropriate apparatus for receiving and may transmit signals via appropriate apparatus for transmitting radio signals. In FIG. 3, a transceiver apparatus is designated schematically by block 306. The transceiver apparatus 306 may be provided for example by means of a radio part and associated antenna arrangement. The antenna arrangement may be arranged internally or externally to the mobile device. The communication device 300 may be provided with at least one processor 301, at least one memory ROM 302a, at least one RAM 302b and other possible components 303 for use in software and hardware aided execution of tasks it is designed to perform, including control of access to and communications with access systems and other communication devices. The at least one processor 301 is coupled to the RAM 302b and the ROM 302a. The at least one processor 301 may be configured to execute an appropriate software code 308. The software code 308 may for example allow to perform one or more of the present aspects. The software code 308 may be stored in the ROM 302a. The communication device 300 may comprise one or more circuits, or circuitry (not shown) which may be configured to perform one or more of the present aspects or examples. The processor, storage and other relevant control apparatus may be provided on an appropriate circuit board and / or in chipsets. This feature is denoted by reference 304. The communication device may optionally have a user interface such as keypad 305, touch sensitive screen or pad, combinations thereof or the like. Optionally one or more of a display, a speaker and a microphone may be provided depending on the type of the device. FIG. 5 shows an example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting. In the example of FIG. 5, the communication device (e.g., a UE) and the network entity (e.g., a base station) are configured to communicate with each other so that the communication device is able to provide CSI report(s) to the network. The example of FIG. 5 may be related to UE-sided beam prediction. The features of FIG. 5 may be applicable for both BM-Case1 and BM-Case2. At S501, the UE reports (or transmits), to the base station, information comprising: a first number for CSI processing, and a second number for CSI processing. The first number is associated with Al-related CSI processing (e.g., Al and / or ML-related CSI processing) that is supported at the UE. The second number is associated with (any type of) CSI processing that is supported at the UE. Stated differently, the first number is associated with AI / ML-related processing for CSI specifically, whereas the second number is associated with CSI processing in general. In some examples, the UE may report that the UE supports beam prediction with associated feature groups (e.g., UE capabilities) that are associated with the beam prediction at the UE side. The first number for CSI processing may comprise a number, NCPU ML , of CSI calculations, for AI / ML-related CSI processing, that are supported by the UE. The second number for CSI processing may comprise a number, NCPU , of CSI calculations, for CSI processing, that are supported by the UE. The number, NCPUiML and / or the number, NCPU , may be representative of simultaneous CSI calculations that are supported. In this context, simultaneous calculations may mean, a number of calculations that may be performed within a predetermined time period (e.g., a (single) orthogonal frequency division multiplex (OFDM) symbol). The UE may indicate the number of simultaneous CSI calculations NCPU and / or NCPUiML per component carrier (CC) with a parameter (e.g., simultaneousCSI-ReportsPerCC), and / or for all components carriers with a parameter (e.g., simultaneousCSI-ReportsAIICC). For example, in 3GPP Rel-19, the number of (simultaneous) calculations to be reported may be a number less than 8 for a CC, or less than 32 for all CCs. The numbers reported by the UE are subject to the capability / capacity (e.g., hardware capability) of the UE. It should be understood that the values above are given as examples only. In other examples, the number per CC may be equal to, or higher than 8, and the number for all CCs may be equal to, or higher than 32. The first number may be representative of a maximum limit for the number of processing unit / CPU calculations for AI / ML-related CSI reports. The second number may be representative of a maximum limit for the number of processing unit / CPU calculations for (any type of) CSI reports. For example, the UE indicates the first number per CC with parameter simultaneousCSIML-ReportsPerCC, and across all CCs with parameter simultaneousCSIML-ReportsAIICC. This indication(s) may be in addition to the reported UE capability of NCPU. The providing of the indications, to the network, may be useful so that the network is informed with regard to certain hardware limitations at the UE (e.g., AI / ML hardware accelerators of the UE) by mapping such limitations to processing units for CSI. In some examples, the UE may also report, to the network entity, a number of AI / ML functionalities (e.g., CSI reporting related functionalities), L, that may be activated (simultaneously) in a CC. The number of AI / ML functionalities, per CC, may be comprised in the parameter maxCSIML-ReportsPerCC. In some examples, the UE may also provide, to the network entity, a reporting of a number of AI / ML functionalities (e.g., CSI reporting related functionalities), L, that may be activated (simultaneously) across all CCs. The number of AI / ML functionalities, across all CCs, may be comprised in the parameter maxCSIML-ReportsPerAIICC. At S502, the base station provides, to the UE, a configuration for CSI. The configuration for CSI is based on the information reported by the UE. In some examples, based on at least one of following: the reported information, or the reported capabilities of the UE, the base station provides a configuration for the UE to report one or more predicted RS resources with a (single) AI / ML functionality (e.g., one ML-enabled CSI reporting configuration) or multiple AI / ML functionalities (e.g., multiple ML-enabled CSI reporting configuration). Each AI / ML functionality may enable beam prediction at the UE. For example, the UE may be configured to report up to top-K beams (e.g., top-K predicted RS resources). The ‘top’ beam may be one a beam with a highest predicted RSRP / SINR. At S503, the UE generates at least one CSI report associated with AI / ML CSI processing based (at least partly) on the information (that was reported to the network). The at least one CSI report may be generated based on (or according to) the configuration received from the network. The at least one CSI report is associated with an AI / ML-enabled feature (e.g., beam prediction). Processing of the at least one CSI report occupies a number of processing units (e.g., CPUs), at the UE, for a length of time (e.g., a number of ODFM symbols). A UE has hardware limitations with regard to how many CSI reports the UE may process at a time. Furthermore, the UE has hardware limitations with regard to how many CSI reports associated with AI / ML that the UE may process at a time. In some examples, the UE determines a maximum number (M) of CSI reports that are supported at the UE for processing based on the information. The number, M, of CSI reports, may be useful for the UE, as the UE may then know whether the at least one CSI report may be generated at a certain time (or if it needs to be delayed until a further time). For example, the determination of the number, M, may be based on at least one of the following: the first number (e.g., NCPUiML) and the second number (e.g., NCPU), when determining CSI reports for CSI calculations. For example: If N CSI reports (i.e., N number of CSI reports) start to occupy respective CPUs on an OFDM symbol and L number of CPU calculations are used / occupied, then NCPU - L are unoccupied; and If K number of CSI reports (wherein K<N) are associated with AI / ML-enabled CSI processing and Lml number of CPU calculations for AI / ML are used / occupied, then ncpu,ml ~Lml CPUs are unoccupied, where each CSI report n=0,...,N-1 corresponds to (wherein 0CPU is a number of CSI processing units); - Then, the UE does not update N-M requested CSI reports with the lowest priority (e.g., according to CSI report priority levels, wherein each CSI report has a priority level / priority value), where 0<M<N is the largest value, and when the equation 2^=01 0^1 <NCPU - L holds and Zn=o °Su,ML <NCPU,ML - Lml holds (if the n’th CSI report is non-ML, M, = 0). When performing CSI processing, a UE may drop one or more lowest priority CSI reports if the UE does not have enough available CSI processing units to process all CSI reports in a given orthogonal frequency division multiplex OFDM symbol. Stated differently, the UE determines the maximum number (M) of CSI reports by: determining whether a number of calculations for CSI processing, at the UE within the first OFDM symbol, associated with an AI / ML model is less than or equal to the first number, and determining whether a total number of calculations for CSI processing, at the UE, within the first OFDM symbol, is less than or equal to the second number. In response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, the UE is able to generate the at least one CSI report. In some examples, a number of processing units at the UE allocated for AI / ML-enabled CSI processing is configured at the UE to be a fixed number, x. The configured number, x, may be to be a higher number than 0CPU = 1. The fixed number, x, may be based on a quantity that is reported in a CSI report. For example, 0CPU = x for a CSI report with CSI-ReportConfig with higher layer parameter reportQuantity set to predicted CRI (Peri), predicted SSB (Pssb-lndex), 'Pcri-PRSRP, 'Pssb-Index-PRSRP. Here, the P suffix indicates predicted CSI quantities associated with beam reporting. For example, Peri is predicted CSI-RS resource indicator. In some examples, the at least one CSI report is generated based on the fixed number, x, associated with the at least one CSI report. At S504, the UE provides (or transmits), to the base station, the at least one CSI report. FIG. 6 shows an example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting. In the example of FIG. 6, the communication device (e.g., a UE) and the network entity (e.g., a base station) are configured to communicate with each other so that the communication device is able to provide CSI report(s) to the network. The example of FIG. 6 may be related to UE-sided beam prediction. The features of FIG. 6 may be applicable for both BM-Case1 and BM-Case2. At S601, the UE reports, to a base station, information related to a first number for CSI processing. The first number is associated with Al-related CSI processing (e.g., AI / ML-related CSI processing) that is supported at the UE. In some examples, the information related to the first number for CSI processing comprises one of: a number, 0CPU f , of CSI processing units, for AI / ML-related CSI processing, that are supported at the UE, or at least one parameter (e.g., K1, K2) that may be used for determining the number, OCPUj , of CSI processing units, for AI / ML-related CSI processing, that are supported at the UE. In some examples, the number, 0CPUj , of CSI processing units is reported: per AI / ML-related functionality, or for any AI / ML-related functionality. In some examples, further information is reported to the base station. The further information comprises at least one of the following: a second number, NCpu,ml , of CSI calculations, for AI / ML-related CSI processing, that are supported by the UE, or a third number, NCPU , of CSI calculations, for all CSI processing, that are supported by the UE. The second and third number may indicate support within a time period (e.g., number of calculations per OFDM symbol). In some examples, the at least one parameter may be indicated per functionality, or for any functionality. For example, when the reported information about processing units / CPUs are dependent on functionality, the dependency may be defined based on quantities reported by the functionality (e.g., depending on an ML model output). In some examples, the UE may also report, to the network entity, a number of AI / ML functionalities (e.g., CSI reporting related functionalities), L, that may be activated (simultaneously) in a CC. The number of AI / ML functionalities, per CC, may be comprised in the parameter maxCSIML-ReportsPerCC. In some examples, the UE may also provide, to the network entity, a reporting of a number of AI / ML functionalities (e.g., CSI reporting related functionalities), L, that may be activated (simultaneously) across all CCs. The number of AI / ML functionalities, across all CCs, may be comprised in the parameter maxCSIML-ReportsPerAIICC. At S602, the base station provides, to the UE, a configuration for CSI. The configuration for CSI is based on the information reported by the UE. In some examples, based on at least one of following: the reported information, or the reported capabilities of the UE, the base station provides a configuration for the UE to report one or more predicted RS resources with a (single) AI / ML functionality (e.g., one ML-enabled CSI reporting configuration) or multiple AI / ML functionalities (e.g., multiple ML-enabled CSI reporting configuration). Each AI / ML functionality may enable beam prediction at the UE. For example, the UE may be configured to report up to top-K beams (e.g., top-K predicted RS resources). The ‘top’ beam may be one a beam with a highest predicted RSRP / SINR. At S603, the UE determines a number of processing units (e.g., CPUs) of the UE to use for processing a CSI report, wherein the UE determines the number of processing units based on the information. The CSI report is associated with an AI / ML-enabled CSI processing. In some examples, the determining of the number of processing units is further based on a quantity being reported in the CSI report. For example, the number of processing units determined may be different, depending on the quantity (e.g., CRI, PMI, RI) being reported in the CSI report. The UE then generates, based on the determining (of the number of processing units), the CSI report using utilising at least one processing unit at the UE. In some examples, the number of processing units for an AI / ML-enabled CSI report may be determined, by the UE, based on the reported capability, 0CPUf (depending on functionality f). In this example, the functionality is associated with the configuration with CSI reporting. The number of processing units is therefore dependent on the configuration for CSI reporting. For example, 0CPU = 0CPUj} may be determined for a CSI report with CSI-ReportConfig_f1 with (higher layer parameter) that has a quantity to be reported (e.g., reportQuantity) set to 'Peri’, or 'Pssb-lndex’. 0CPU = 0CPUj2 may be determined for a CSI report with CSI-ReportConfig_f2 with (higher layer parameter) that has a quantity to be reported set to 'Pcri-PRSRP’, or 'Pssb-lndex-PRSRP’. In some examples, the number of processing units for AI / ML-enabled CSI report may be determined, by the UE, based on the reported parameters (e.g., K1 and K2) (depending on functionality f). K1 and K2 may be associated with ML model output types (or types of CSI quantities to be reported). For example, OCPU = KI is determined for a CSI report with CSI-ReportConfig_f1 with a quantity to be reported (e.g., reportQuantity) is set to 'Peri’ or 'Pssb-lndex’. 0CPU = K1 + K2 may be determined for a CSI report with CSI-ReportConfig_f2 with a quantity to be reported is set to 'Pcri-PRSRP’ or 'Pssb-lndex-PRSRP’. In examples whereby NCPU ML is reported to the network entity (e.g., in S601), the UE may determine a maximum number of CSI reports (M) based on the second number and the third number, when determining the applicable CSI reports for CSI calculations. In examples whereby NCPUML\s not reported to the network entity (e.g., there is no limit for AI / ML-enabled CSI processing units across CSI reports), the UE determines a number of CSI reports based on the third number (e.g., NCPU). For example, if N CSI reports (i.e., N number of CSI reports) start to occupy respective CPUs on an OFDM symbol and L number of CPU calculations are used / occupied, then NCPU - L are unoccupied, wherein each CSI report n = 0,..., N - 1 corresponds to 0^, then the UE is not required to update the N - M requested CSI reports with lowest priority, when 0 <M <N is the largest value and ^O^U<NCPU-L holds. At S604, the UE provides, to the base station, the CSI report. FIG. 7 shows an example signalling and operations diagram between a communication device and a network entity associated with CSI processing and reporting. In the example of FIG. 7, the communication device (e.g., a UE) and the network entity (e.g., a base station, gNB) are configured to communicate with each other so that the communication device is able to provide CSI report(s) to the network. The example of FIG. 7 may be related to UE-sided beam prediction. The features of FIG. 7 may be applicable for both BM-Case1 and BM-Case2. At S701, the UE receives at least one configuration (e.g., via RRC) for CSI. The at least one configuration may comprise at least one of the following: a configuration for CSI measurement (e.g., CSI-MeasConfig), a configuration for CSI reporting (e.g., CSI-ReportConfig), other configurations for CSI measurement, or reporting parameters. The at least one configuration may comprise at least one CSI-ReportConfig (e.g., CSI-ReportConfig_x) that is enabling ML beam prediction at the UE side. At S702, DL RS transmissions are sent from the gNB to the UE. The UE may measure the DL RS transmissions whenever the beam reporting for CSI-ReportConfig_x is applicable. At S703, the gNB sends triggering commands to activate a CSI report at the UE (e.g., related to CSI-ReportConfig_x). The gNB may send the triggering command when the CSI report is for aperiodic (AP)-CSI reporting. At S704, the UE determines a number of processing units (e.g., CPUs) that will be utilized for processing a CSI report based on CSI-ReportConfig_x. For example, the UE may determine the number of processing units based on information reported to the network about supported processing units (e.g., similar to the reporting in S501 and S601 in FIG.5 and FIG. 6 respectively). For example, the information may be related to the first number for CSI processing comprises one of: a number, 0CPUif , of CSI processing units, for Al-related CSI processing (e.g., AI / ML-related CSI processing), that are supported at the UE, or at least one parameter (e.g., K1, K2) that may be used for determining the number, 0CPUf , of CSI processing units, for AI / ML-related CSI processing, that are supported at the UE. In this example, the UE determines a number of CSI processing units to be used to process the CSI report. The number of CSI processing units is ‘xT. The x1 number of CSI processing units may be a single processing unit, in some examples. In other examples, the x1 number of processing units is representative of a plurality of processing units. In some examples, the UE performs determinations similar to at least one of the features of S503 from FIG. 5 and / or S603 from FIG. 6. At S705, inference for an Al mode (or AI / ML model) is performed at the UE. The inference utilises the x1 number of CSI processing units. The inference may be associated with a configuration received by the UE (e.g., CSI-ReportConfig_x). For example, the AI / ML model may be used for a beam prediction. Measurements performed by the UE may be used as an input to the AI / ML model. In this example, an ‘ML model LT is utilised at the UE. The ML model L1 is associated with the CSI-ReportConfig_x. In this example, the ML model L1 provides a predicted ‘best’ beam. In this context, a ‘best’ beam is a beam that has a predicted highest RSRP or SINR. It should be understood that ‘ML model LT is an example only. Any suitable Al or ML model may be used that has any suitable function or output (e.g., CSI compression, CSI prediction, etc.). At S706, the UE provides the CSI report to the gNB. The beam report may comprise a CRI based on the determination in S705. As per the determination of S704, the processing (and transmission) of the CSI report is occupying the ‘xT number of CSI processing units. At S707, the AI / ML model associated with the CSI-ReportConfig_x changes (for the beam prediction). For example, UE may receive instructions or determine switch to a different AI / ML model (e.g., change to ‘ML model L2’). This change may be due to performance issues or complexity concerns observed at the UE and / or NW. In some examples, when a CSI report is associated with an AI / ML-enabled feature, the number of CSI processing units (0CPU) considered for the CSI report may undergo changes. The changes on the number of CSI processing units may be due to one of the following: When models are identified at the network, the model may be identified with an identity (e.g., model-ID), and the CSI report may be associated with m models (m = 1, ..., M), wherein M is the maximum number of models that may be associated with a CSI report. Each model of m models may be associated with a number of CSI processing units (e.g., the i’th model may be associated with OCPUl). When models are not identified at the network (e.g., when UE ML models are transparently handled by the UE), a CSI report may be associated with more than one CSI processing unit (OCPU= x2, ..xm), wherein a AI / ML model used by the UE may change the number of CSI processing units considered for the CSI report. At S708, the UE determines a number of processing units that will be utilized for processing a CSI report according to CSI-ReportConfig_x. The determination of the number of processing units may be considered to be an updated determination, based on the model changing to ML model L2. The UE determines a number of CSI processing units to be used to process a further CSI report that is based on CSI-ReportConfig_x. The number of CSI processing units determined is ‘x2’. The x2 number of CSI processing units may be a single processing unit, in some examples. In other examples, the x1 number of processing units is representative of a plurality of processing units. In this example, it is assumed that the number of processing units of x1 is different to the number of processing units of x2. Stated differently, the processing of the further CSI report utilises a different number of processing units compared to the processing of the CSI report. In some examples, the UE performs determinations similar to at least one of the features of S503 from FIG. 5 and / or S603 from FIG. 6. When the UE switches the ML model to ML model L2, there is a change in the number of processing units that are to be occupied / utilised for the CSI-reportConfig_x, in this example. At S709, the UE reports a number of processing units associated with CSI-ReportConfig_X to the gNB. For example, the UE reports information related to the x2 number of processing units. The change on the number of processing units associated with the CSI report may be reported by the UE via UE-initiated or UE-triggered message. The change on the number of processing units associated with the CSI report may be considered for the next instance that the CSI report becomes valid for reporting. The reporting (by the UE to the gNB) may comprise a medium access control control element (MAC-CE) message. A field of the MAC-CE may include at least one of the following: at least one identity for a CSI reporting configuration, or a parameter that allows the determination of the associated number of CSI processing units. At S710, the gNB provides, to the UE, an acknowledgement (ACK) or negative ACK (NACK) with regard to the message of S709. At S711, inference for the AI / ML model is performed at the UE. The inference utilises the x2 number of processing units. The inference is associated with the configuration received by the UE (e.g., CSI-ReportConfig_x). In this example, the ‘ML model L2’ is utilised at the UE. The ML model L2 is associated with the CSI-ReportConfig_x. In this example, the ML model L2 provides a predicted ‘best’ beam. At S712, the UE provides a further CSI report to the gNB. The beam report may comprise a CRI based on the determination in S711 (or information related to the CRI). As per the determination of S708, the processing (and transmission) of the further CSI report is occupying the ‘x2’ number of processing units. It should be understood that one or more of the features / steps described in any of FIGS. 5 to 8 may not be performed in some examples, or may be performed in a different order. It should be understood that the AI / ML models described in FIGS. 5 to 8 are described as examples only. Any suitable Al model, ML model (or the like) may be utilised. One or more of the examples described above have the advantage that hardware limitations that are specific to Al and / or ML models that are utilised for CSI processing are taken into account when configurating and generating CSI reports. The UE is able to perform determinations with regard to total capacity for CSI processing and a capacity that is specifically for CSI processing that uses AI / ML models. CSI processing units (CPUs) are used to ensure consistent UE behavior (which is important to the network) when handling multiple CSI reports. Without knowing the number of CPUs for a CSI report and any total limit across all CSI reports, UEs often exceed hardware limitations that the UE has. This leads to UEs dropping CSI reports, and the network may not know which CSI reports are reported. Therefore, one or more of the examples have the advantage that there is a reduced likelihood of UE dropping CSI reports. Furthermore, the UE determines changes associated with the AI / ML model being used for CSI report. This has the advantage of improved flexibility for the UE to change the number of CSI processing units for an AI / ML-enabled CSI report when an applicable ML model is changed FIG. 8 shows an example method flow performed by an apparatus. The apparatus may be, for example, a communication device, a UE, a terminal, a mobile device, etc. The apparatus may comprise one or more means for performing the method of FIG. 8. For example, the means may comprise at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform the method of FIG. 8. In S801, the method comprises reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus. In S803, the method comprises generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with Al related CSI processing. In S805, the method comprises providing, to the network entity, the at least one CSI report. FIG. 9 shows another example method flow performed by an apparatus. The apparatus may be, for example, a network entity. The network entity may be a base station, gNB, core network entity, etc. At S901, the method comprises receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device. At S903, the method comprises providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information. At S905, the method comprises receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration. FIG. 10 shows a schematic representation of non-volatile memory media 1000a (e.g. Blu-ray disc (BD), computer disc (CD) or digital versatile disc (DVD)) and 1000b (e.g. flash memory, solid state memory, universal serial bus (USB) memory stick) storing instructions and / or parameters 1002 which when executed by a processor allow the processor to perform one or more of the steps of the method of FIGS. 8 to 9. It is noted that while the above describes example embodiments, there are several variations and modifications which may be made to the disclosed solution without departing from the scope of the present invention. The examples may thus vary within the scope of the attached claims. In general, some embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although embodiments are not limited thereto. While various embodiments may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as nonlimiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof. The examples may be implemented by computer software stored in a memory and executable by at least one data processor of the involved entities or by hardware, or by a combination of software and hardware. Further in this regard it should be noted that any procedures may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on such physical media as memory chips, or memory blocks implemented within the processor, magnetic media such as hard disk or floppy disks, and optical media such as for example DVD and the data variants thereof, CD. The term “non-transitory”, as used herein, is a limitation of the medium itself (i.e. tangible, not a signal) as opposed to a limitation on data storage persistency (e.g. RAM vs ROM). As used herein, “at least one of the following:” and “at least one of: ” and similar wording, where the list of two or more elements are joined by “and”, or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all of the elements. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The data processors may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASIC), gate level circuits and processors based on multi core processor architecture, as non-limiting examples. As used herein, the term “means for”, “means for performing the operations”, or “means configured to perform” (or similar) may be any means that are suitable for performing the feature. The “means” may be configured to perform one or more of the functions and / or method steps previously described. For example, the “means” may include one or more of: at least one processor, at least one memory, transceiver circuitry, antenna circuitry, etc. It should be understood that these are provided as non-limiting examples. Alternatively, or additionally some examples may be implemented using circuitry. The circuitry may be configured to perform one or more of the functions and / or method steps previously described. That circuitry may be provided in the base station and / or in the communications device. As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analogue and / or digital circuitry); (b) combinations of hardware circuits and software, such as: (i) a combination of analogue and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as the communications device or base station to perform the various functions previously described; and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to uses of the term “means” in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example integrated device. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in a server, a cellular network device, or other computing or network device. The foregoing description has provided by way of exemplary and non-limiting examples a full and informative description of some embodiments. However, various modifications and adaptations may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications of the teachings will still fall within the scope as defined in the appended claims.

Claims

1. An apparatus comprising:means for reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus;means for generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; and means for providing, to the network entity, the at least one CSI report.

2. The apparatus according to claim 1, wherein the first number for CSI processing comprises:a number, NCPUiML , of CSI calculations, for Al related CSI processing, that are supported by the apparatus.

3. The apparatus according to claim 1 or claim 2, wherein the second number for CSI processing comprises:a number, NCPU , of CSI calculations, for CSI processing, that are supported by the apparatus.

4. The apparatus according to any of claims 1 to 3, wherein the second number for CSI processing is associated with all CSI processing supported at the apparatus.

5. The apparatus according to any of claims 1 to 4, wherein the first number is reported within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers.

6. The apparatus according to any of claims 1 to 5, wherein the apparatus comprises: means for receiving, from the network entity, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the information that has been reported, wherein the at least one CSI report is generated based, at least partly, on the configuration.

7. The apparatus according to any of claims 1 to 6, wherein the apparatus comprises:means for determining a maximum number of CSI reports that the apparatus is capable of processing within a first orthogonal frequency division multiplex, OFDM, symbol, wherein the determining is based on the information.

8. The apparatus according to claim 7, wherein the means for determining the maximum number comprises:means for determining whether a number of calculations for CSI processing, at the apparatus within the first OFDM symbol, associated with an Al related CSI processing is less than or equal to the first number;means for determining whether a total number of calculations for CSI processing, at the apparatus within the first OFDM symbol, is less than or equal to the second number; andmeans for, in response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, generating the at least one CSI report.

9. The apparatus according to any of claims 1 to 8, wherein a number of processing units, 0CPU , comprised within the apparatus that are available for processing the at least one CSI report associated with the Al related model has a first value, OCPU = x ,wherein the first value is dependent on a quantity being reported in the at least one CSI report.

10. The apparatus according to any of claims 1 to 9, wherein the apparatus is one of: a communication device, a user equipment, or a terminal.

11. A method performed by an apparatus, the method comprising:reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus;generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; andproviding, to the network entity, the at least one CSI report.

12. The method according to claim 11, wherein the first number for CSI processing comprises:a number, NCPUiML , of CSI calculations, for Al related CSI processing, that are supported by the apparatus.

13. The method according to claim 11 or claim 12, wherein the second number for CSI processing comprises:a number, NCPU , of CSI calculations, for CSI processing, that are supported by the apparatus.

14. The method according to any of claims 11 to 13, wherein the second number for CSI processing is associated with all CSI processing supported at the apparatus.

15. The method according to any of claims 11 to 14, wherein the first number is reported within one of: a first parameter that is per component carrier, or a second parameter that is for all component carriers.

16. The method according to any of claims 11 to 15, further comprising:receiving, from the network entity, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the information that has been reported,wherein the at least one CSI report is generated based, at least partly, on the configuration.

17. The method according to any of claims 11 to 16, further comprising:determining a maximum number of CSI reports that the apparatus is capable of processing within a first orthogonal frequency division multiplex, OFDM, symbol, wherein the determining is based on the information.

18. The method according to claim 17, wherein the determining the maximum number comprises:determining whether a number of calculations for CSI processing, at the apparatus within the first OFDM symbol, associated with an Al related CSI processing is less than or equal to the first number;determining whether a total number of calculations for CSI processing, at the apparatus within the first OFDM symbol, is less than or equal to the second number; andin response to determining that both the number of calculations for CSI processing is less than or equal to the first number and the total number of calculations for CSI processing is less than or equal to the second number, generating the at least one CSI report.

19. The method according to any of claims 11 to 18, wherein a number of processing units, 0CPU , comprised within the apparatus that are available for processing the at least one CSI report associated with the Al related model has a first value, OCPU = x ,wherein the first value is dependent on a quantity being reported in the at least one CSI report.

20. The method according to any of claims 11 to 19, wherein the apparatus is one of: a communication device, a user equipment, or a terminal.

21. A computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform at least the following:reporting, to a network entity, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the apparatus, and wherein the second number is associated with CSI processing that is supported at the apparatus;generating at least one CSI report based, at least partly, on the information, wherein the at least one CSI report is associated with the Al related CSI processing; andproviding, to the network entity, the at least one CSI report.

22. An apparatus comprising:means for receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device;means for providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; andmeans for receiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration.

23. The apparatus according to claim 22, further comprising:means for determining the configuration for CSI reporting based, at least partly, on the information that has been received, wherein the configuration is associated with the Al related CSI processing.

24. A method performed by an apparatus, the method comprising:receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device;providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; andreceiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration.

25. A computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform at least the following:receiving, from a communication device, information comprising: a first number for channel state information, CSI, processing, and a second number for CSI processing, wherein the first number is associated with artificial intelligence, Al, related CSI processing that is supported at the communication device, and wherein the second number is associated with CSI processing that is supported at the communication device;providing, to the communication device, a configuration for CSI reporting, wherein the configuration is associated with the Al related CSI processing and is based on the received information; andreceiving, from the communication device, at least one CSI report, wherein the at least one CSI report is associated with the Al related CSI processing and has been generated based, at least partly, on the configuration.

Images