Selected Patent Applications

Dynamic quantization and memory management of key-value cache for serving large language models. S. Gobriel, N. Jain, V. Chua, J. Pablo Muñoz, G. Jha. US Patent App. 18/934,700. 2025

Methods and aparatus for enabling unstructured sparsity in low-precision large pre-trained foundation model. J. Pablo Muñoz, Jinjie Yuan, Nilesh Jain. 2024

Frameworks for training of federated learning models. Rohit Verma, Arun Raghunath, J. Pablo Muñoz, Nilesh Jain. 2024

Methods and apparatus to modify pre-trained models to apply neural architecture search. J. Pablo Muñoz, N. Jain, C. Lacewell, A. Kozlov, N. Lyalyushkin, V. Shamporov, A. Senina. PCT/US2022/032721. 2022

Methods and apparatus for dynamic xpu hardware-aware deep learning model management. R. Iyer, N. Jain, J. Pablo Muñoz, E. Nurvitadhi, A. Bhiwandiwalla et al. U.S. Patent App. 17/645,742. 2022.

Methods and apparatus for data enhanced automated model generation. C. Lacewell, J. Pablo Muñoz, R. Poornachandran, N. Jain, A. Bhiwandiwalla et al. U.S. Patent App. 17/559,730. 2022.

Apparatus, articles of manufacture, and methods for composable machine learning compute nodes. E. Nurvitadhi, R. Poornachandran, A. Davare, N. Jain, C. Lacewell, J. Pablo Muñoz. U.S. Patent App. 17/558,284. 2022.

Machine learning model scaling system with energy efficient network data transfer for power aware hardware. D. Cummings, J. Pablo Muñoz, S. Kundu, S. Sridhar, M. Szankin. U.S. Patent App. 17/506,161. 2022.

Framework for optimization of machine learning architectures. A. Sarah, D. Cummings, J. Pablo Muñoz, T. Webb. U.S. Patent App. 17/505,568. 2022.

Environment specific model delivery. J. Pablo Muñoz, I. Alvarez, N. Jain, C. Lacewell U.S. Patent App. 17/131,680. 2021.

Optimizing charging, fueling, and parking overheads of fleet vehicles in a MAAS architecture. J. Pablo Muñoz, I. Alvarez, A. Merwaday, S. Jha, N. Smith, V. Banjade, et al. U.S. Patent App. 17/131,704. 2021.