# US 2026/0099355 A1 · Methods and apparatus to optimize artificial intelligence inference workloads on audio and video data streams > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0099355 A1 - Document ID: US20260099355A1 - Status: Published application - Kind: A1 - Application number: 18/909,646 - Filed: 2024-10-08 - Published: 2026-04-09 - Earliest claimed: 2024-10-08 - Assignees: McAfee, Inc. - Applicants: McAfee, LLC - Inventors: Steven Leonard Grobman; German Lancioni - Web page: https://patentgrep.com/patent/US20260099355A1 ## CPC - G06F 9/485: {Task life-cycle, e.g. stopping, restarting, resuming execution (G06F9/4881 takes precedence)} - G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals} - G06F 9/5094: {where the allocation takes into account power or heat criteria (power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Systems, apparatus, articles of manufacture, and methods are disclosed to reduce a use of a compute engine executing dense layers in a model. An example apparatus includes obtain a first vector generated by an initial layer of the model, the first vector corresponding to a first data frame, wherein the initial layer of the model utilizes less computation resources than the dense layer is to utilize, measure a similarity between the first vector and a prior vector, wherein the prior vector has been classified by the model and corresponds to a second data frame occurring before the first data frame represented by the first vector, determine that the first vector satisfies a similarity threshold to the prior vector, and instruct the compute engine to enter an idle state, the idle state to suspend execution of the dense layers in the model. ## Claims ### Claim 1 An apparatus to reduce a use of a compute engine executing dense layers in a model, the apparatus comprising: interface circuitry; machine readable instructions; and programmable circuitry to at least one of instantiate or execute the machine readable instructions to: obtain a first vector generated by an initial layer of the model, the first vector corresponding to a first data frame, wherein the initial layer of the model utilizes less computation resources than the dense layers are to utilize; measure a similarity between the first vector and a prior vector, wherein the prior vector has been classified by the model and corresponds to a second data frame occurring before the first data frame represented by the first vector; determine that the first vector satisfies a similarity threshold to the prior vector; and instruct the compute engine to enter an idle state, the idle state to suspend execution of the dense layers in the model. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the first data frame is a frame of audio or video. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the programmable circuitry is to store the first vector in a cache with a same classification as the classification of the similar prior vector. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the compute engine is a first compute engine and the initial layer of the model is executed by a second compute engine different from the first compute engine. ### Claim 5 (depends on 4) The apparatus of claim 4, wherein the first compute engine is a graphics processing unit (GPU) or a neural processing unit (NPU) and the second compute engine is a central processing unit (CPU), wherein the first compute engine and the second compute engine operate to execute the model. ### Claim 6 (depends on 4) The apparatus of claim 4, wherein the initial layer of the model is to process the first data frame into the first vector that is representative of features of the first data frame that are to be analyzed by the second compute engine during classification of the first vector. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein the programmable circuitry is to: obtain a second vector generated by the initial layer of the model and corresponding to a third data frame; measure a similarity between the second vector and prior vectors, the prior vectors including the first vector and the prior vector; determine that the second vector does not satisfy the similarity threshold to the prior vectors; and instruct a compute engine executing additional layers of the model to classify the second vector, wherein the instruction is to cause the compute engine to switch to an awake state to prepare for classification. ### Claim 8 A non-transitory machine readable storage medium to reduce a use of a compute engine executing dense layers in a model comprising machine readable instructions to cause programmable circuitry to at least: obtain a first vector generated by an initial layer of the model, the first vector corresponding to a first data frame, wherein the initial layer of the model utilizes less computation resources than the dense layers are to utilize; measure a similarity between the first vector and a prior vector, wherein the prior vector has been classified by the model and corresponds to second data frames occurring before the first data frame represented by the first vector; determine that the first vector satisfies a similarity threshold to the prior vector; and instruct the compute engine to enter an idle state, the idle state to suspend execution of the dense layers in the model. ### Claim 9 (depends on 8) The at least one non-transitory machine readable storage medium of claim 8, wherein the first data frame is a frame of audio or video. ### Claim 10 (depends on 8) The at least one non-transitory machine readable storage medium of claim 8, wherein the machine readable instructions are to cause the programmable circuitry to is to store the first vector in a cache with a same classification as the classification of the similar prior vector. ### Claim 11 (depends on 8) The at least one non-transitory machine readable storage medium of claim 8, wherein the compute engine is a first compute engine and the initial layer of the model is executed by a second compute engine different from the first compute engine. ### Claim 12 (depends on 11) The at least one non-transitory machine readable storage medium of claim 11, wherein the first compute engine is a graphics processing unit (GPU) or a neural processing unit (NPU) and the second compute engine is a central processing unit (CPU), wherein the first compute engine and the second compute engine operate to execute the model. ### Claim 13 (depends on 11) The at least one non-transitory machine readable storage medium of claim 11, wherein the initial layer of the model is to process the first data frame into the first vector that is representative of features of the first data frame that are to be analyzed by the second compute engine during classification of the first vector. ### Claim 14 (depends on 8) The at least one non-transitory machine readable storage medium of claim 8, wherein the machine readable instructions are to cause the programmable circuitry to: obtain a second vector generated by the initial layer of the model and corresponding to a third data frame; measure a similarity between the second vector and prior vectors, the prior vectors including the first vector and the prior vector; determine that the second vector does not satisfy the similarity threshold to the prior vectors; and instruct a compute engine executing additional layers of the model to classify the second vector, wherein the instruction is to cause the compute engine to switch to an awake state to prepare for classification. ### Claim 15 A server to distribute first software instructions on a network to reduce a use of a compute engine executing dense layers in a model, the server comprising: at least one storage device including second instructions; and at least one processor to execute the second instructions to transmit the first software instructions over the network, the first software instructions, when executed, to cause at least one device to: obtain a first vector generated by an initial layer of the model, the first vector corresponding to a first data frame, wherein the initial layer of the model utilizes less computation resources than the dense layers are to utilize; measure a similarity between the first vector and a prior vector, wherein the prior vector has been classified by the model and corresponds to second data frames occurring before the first data frame represented by the first vector; determine that the first vector satisfies a similarity threshold to the prior vector; and instruct the compute engine to enter an idle state, the idle state to suspend execution of the dense layers in the model. ### Claim 16 (depends on 15) The server of claim 15, wherein the first data frame is a frame of audio or video. ### Claim 17 (depends on 15) The server of claim 15, wherein the first software instructions are to cause the at least one device to store the first vector in a cache with a same classification as the classification of the similar prior vector. ### Claim 18 (depends on 15) The server of claim 15, wherein the compute engine is a first compute engine and the initial layer of the model is executed by a second compute engine different from the first compute engine. ### Claim 19 (depends on 18) The server of claim 18, wherein the first compute engine is a graphics processing unit (GPU) or a neural processing unit (NPU) and the second compute engine is a central processing unit (CPU), wherein the first compute engine and the second compute engine operate together to execute the model. ### Claim 20 (depends on 15) The server of claim 15, wherein the first software instructions are to cause the at least one device to obtain a second vector generated by the initial layer of the model and corresponding to a third data frame; measure a similarity between the second vector and prior vectors, the prior vectors including the first vector and the prior vector; determine that the second vector does not satisfy the similarity threshold to the prior vectors; and instruct a compute engine executing additional layers of the model to classify the second vector, wherein the instruction is to cause the compute engine to switch to an awake state to prepare for classification.