189 citations · 717 across the 25 of their papers we have counts for
4 papers · 1 filter
Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion
Tuna Tuncer, Felix Becker, Thomas Pfeil
Chunk-wise autoregressive video diffusion models rely on a KV cache of previously generated chunks to avoid redundant computation, but this cache quickly becomes a memory bottlenec…
Interactions Across Blocks in Post-Training Quantization of Large Language Models
Khasmamad Shabanovi, Lukas Wiest, Vladimir Golkov +2
Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are q…
SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
Manuel Nonnenmacher, Thomas Pfeil, Ingo Steinwart +1
Pruning neural networks reduces inference time and memory costs. On standard hardware, these benefits will be especially prominent if coarse-grained structures, like feature maps,…
ItNet: iterative neural networks with small graphs for accurate, efficient and anytime semantic segmentation
Thomas Pfeil
Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were devel…