1 citations · 2 across the 3 of their papers we have counts for
3 papers
QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads
Muhammad Ahmad, Khurram Mazher, Saqib Akram +2
We present QuantX: a tailored suite of recipes for LLM and VLM quantization. It is capable of quantizing down to 3-bit resolutions with minimal loss in performance. The quantizatio…
Multi-user Downlink Beamforming using Uplink Downlink Duality with CEQs for Frequency Selective Channels
Khurram Usman Mazher, Amine Mezghani, Robert W Heath
High-resolution fully digital transceivers are infeasible at millimeter-wave (mmWave) due to their increased power consumption, cost, and hardware complexity. The use of low-resolu…
Multi-user Downlink Beamforming using Uplink Downlink Duality with 1-bit Converters for Flat Fading Channels
Khurram Usman Mazher, Amine Mezghani, Robert W. Heath
The increased power consumption of high-resolution data converters at higher carrier frequencies and larger bandwidths is becoming a bottleneck for communication systems. In this p…