The quadratic cost of causal self-attention severely bottlenecks long-context transformer inference. While numerous post hoc linearization pipelines exist, it is difficult to identify which components preserve model quality.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 07706v1 Announce Type: new Abstract: The quadratic cost of causal self-attention severely bottlenecks long-context transformer inference.
arXiv:2606. 01294v1 Announce Type: cross Abstract: Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks.
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
arXiv:2608. 12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length.
arXiv:2607. 06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation.
arXiv:2607. 24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck.