2 results about "Reliable computing" patented technology

This invention provides a method and apparatus for measuring computing power on an intelligent computing cloud platform based on GPU computing power consumption and inference token values. It relates to the fields of intelligent computing centers, smart computing centers, computing infrastructure, and smart computing cloud technologies, and includes the following steps: Step S1, collecting task data, GPU runtime data, and model and engine parameters during inference on the intelligent computing cloud platform; Step S2, extracting first feature information, second feature information, and third feature information from the task data, GPU runtime data, and model and engine parameters; Step S3, performing token fitting computing power calculation based on the first feature information, GPU model, and third feature information to obtain a first computing power consumption value; Step S4, performing GPU computing power consumption benchmark calculation based on the first, second, and third feature information to obtain a second computing power consumption value; Step S5, determining a reliable computing power consumption value based on the first and second computing power consumption values. This invention can significantly improve the accuracy of computing power measurement on intelligent computing center cloud platforms.

This application relates to the field of natural language processing technology, and more particularly to a method for solving mathematical problems using a small-parameter, large-language-model approach and its applications. The method involves a teacher model that structurally decomposes the mathematical problem, providing a reasoning path for the student model. Simultaneously, an external sandbox executor handles all numerical computation tasks, avoiding computational biases and reasoning errors that may arise from greedy decoding, thus achieving reliable computation for small-parameter models in solving mathematical problems. The aim is to address the problem of unreliable mathematical problem-solving caused by greedy decoding in long-term reasoning processes using small models. Without requiring model retraining, this method significantly improves the logical consistency, computational accuracy, and overall robustness of small-parameter models in mathematical reasoning tasks, making it suitable for applications such as mathematical problem solving, enhanced mathematical reasoning, and related intelligent problem-solving systems.