FlashSVD fuses low-rank SVD projections into attention and feed-forward GPU kernels so SVD-compressed transformers avoid materializing dense activations, cutting activation memory at a latency cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
FlashSVD fuses low-rank SVD projections into attention and feed-forward GPU kernels so SVD-compressed transformers avoid materializing dense activations, cutting activation memory at a latency cost.