5 papers
Mask-Guided KV Cache Eviction in Block Diffusion Language Models
Gleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov +2
Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory capacity and generation speed…
Task-Aware QUBO Allocation for Mixed-Precision Quantization
Osama Orabi, Artur Zagitov, Hadi Salloum +2
Mixed-precision quantization requires discrete allocation of weight and activation bit-widths, followed by recovery of the selected network. We develop a task-aware quadratic uncon…
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
Artur Zagitov, Alexander Miasnikov, Maxim Krutikov +5
Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, off…
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
Artur Zagitov, Gleb Molodtsov, Aleksandr Beznosikov
Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains highly sensitive to activatio…
Neural Network Pruning via QUBO Optimization
Osama Orabi, Artur Zagitov, Hadi Salloum +3
Neural network pruning can be formulated as a combinatorial optimization problem, yet most existing approaches rely on greedy heuristics that ignore complex interactions between fi…