5 results about "Autoload" patented technology

A new apparatus and method for securely distributing an application to the processors of a processing unit. The processing unit is formed as part of an integrated circuit and includes a plurality of processors (referred to as tiles), each having their own execution unit and storage for storing application data and additional executable instructions. The integrated circuit includes a hardware module (referred to herein as an autoloader) configured to distribute a set of bootloader instructions (referred to herein as a secondary bootloader) to each of at least some of the tiles. Each of the tiles then executes the instructions of the received secondary bootloader, which causes each tile to issue a read request to read a set of executable application instructions from a memory external to the integrated circuit. Each tile then executes operations using the received set of executable application instructions in order to execute the application using the processing unit.

The application provides a large model inference optimization method, system, medium, terminal and program product for Ascend processors. The method comprises: comparing the automatically detected version with a built-in compatibility table; if the versions do not match, automatically loading a runtime patch or calling a backup library; if the versions match, processing a user request based on a preset hybrid scheduling mechanism; dynamically selecting a MindIE inference framework or a vLLM inference framework based on a runtime adaptation layer according to the user request parameters; converting large model weights into low-bit weights and compensating based on an error compensation matrix; identifying subgraphs and fusing operators for a model graph according to the computing characteristics of the Ascend processor, and rearranging intermediate tensors according to the 512B memory access alignment rule of the Ascend processor; performing pipelined overlap processing on the matrix multiplication calculation of the current token and the full aggregation operation based on an asynchronous execution flow; and performing inference and generating an inference result according to the user request. The application can improve the efficiency and reliability of large model inference.

The application provides a configuration-driven DL4NLP model automatic training and deployment method, which comprises the following steps: parsing a YAML configuration file and verifying parameters to generate a unified process configuration; automatically loading data and performing preprocessing according to the configuration to generate a model input tensor; instantiating model components through a component factory and assembling the model components into a complete network model; automatically configuring a training environment to train and evaluate the model to obtain an optimal model; exporting the model into a TorchScript format binary file; and automatically generating a standardized deployment package based on a template engine. The application abstracts the whole process of model development and deployment into a configuration-driven standardized pipeline by parsing the YAML configuration file, automatically performs data loading and preprocessing, model component instantiation and assembly, training optimization and deployment package generation, and solves the problems of low development efficiency, long cycle and technical gap between training and deployment caused by repeated code writing and manual conversion and deployment for different tasks in traditional model training and deployment.

The invention discloses a Windows handle adaptive program silent automatic loading method and system, and relates to the technical field of program loading.The method comprises the steps that a target process is obtained, and window handles of the target process are enumerated to form a candidate handle set; collecting multi-source rectangular observation of the candidate handles to form historical buffering, and screening, determining and analyzing the handles; the cross-screen mixing degree and the time jitter degree of the handle are calculated and analyzed, and the geometric state of the handle is judged to be a resident state, a half-cross state or a transition state according to a preset threshold value; counting and generating a gating result in the gating time window; when gating is passed, determining a rectangle used in the round according to a geometric state: if the rectangle is in a resident state, adopting a main source mode for selection, and if the rectangle is in a half-span state or a transition state, adopting a fusion mode; and determining a final binding handle in the candidate handle set based on the current round of use of a rectangle, and updating a coordinate mapping relation of silent automatic loading. The method can adapt to multi-display, window cross-screen and jitter scenes, and the accuracy and robustness of automatic loading are improved.

This invention discloses a metadata-driven method and system for constructing a large language model intelligent agent through bootstrapping, relating to the field of artificial intelligence technology. The method includes the following steps: collecting natural language requirements generated from business scenarios and organizing these requirements into a unified expression format; generating readable metadata description content within this unified expression format; performing field splitting and role attribution around the metadata description content; constructing data type definition metadata within the unified expression format; and embedding prompt words into the data type definition metadata to generate content. This invention achieves progressive generation from natural language to data types, rules, and intelligent agent definitions through unified metadata expression, supporting dynamic construction and automatic loading at runtime, reducing manual intervention, and improving automation. Simultaneously, new metadata is generated during runtime and fed back into the generation chain, forming a continuous bootstrapping closed loop, enhancing structural consistency and version evolution controllability.