no code implementations • 22 Mar 2024 • Yassaman Ebrahimzadeh Maboud, Muhammad Adnan, Divya Mahajan, Prashant J. Nair
Training recommendation models pose significant challenges regarding resource utilization and performance.
1 code implementation • 14 Mar 2024 • Muhammad Adnan, Akhil Arunkumar, Gaurav Jain, Prashant J. Nair, Ilya Soloveychik, Purushotham Kamath
This approach effectively reduces both the KV cache size and memory bandwidth usage without compromising model accuracy.
no code implementations • 28 Aug 2023 • Muhammad Adnan, Yassaman Ebrahimzadeh Maboud, Divya Mahajan, Prashant J. Nair
However, deep learning-based recommendation models often face challenges due to evolving user behaviour and item features, leading to covariate shifts.
no code implementations • 20 Jan 2023 • Mansoor Ali, Faisal Naeem, Nadir Adam, Georges Kaddoum, Noor Ul Huda, Muhammad Adnan, Muhammad Tariq
In addition, the impact of disasters on the power system infrastructure is investigated and different types of optimization techniques that can be used to sustain the power flow in the network during disturbances are compared and analyzed.
no code implementations • 11 Apr 2022 • Muhammad Adnan, Yassaman Ebrahimzadeh Maboud, Divya Mahajan, Prashant J. Nair
This approach utilizes CPU main memory for non-popular embeddings and GPUs' HBM for popular embeddings.
1 code implementation • 1 Mar 2021 • Muhammad Adnan, Yassaman Ebrahimzadeh Maboud, Divya Mahajan, Prashant J. Nair
This paper leverages this asymmetrical access pattern to offer a framework, called FAE, and proposes a hot-embedding aware data layout for training recommender models.