arXiv:2607. 21731v1 Announce Type: new Abstract: Transformers are widely used across many domains, including natural language processing, computer vision, web search, and DNA sequence analysis.
arXiv:2602. 21196v2 Announce Type: replace Abstract: Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism.
FlashLoop is a training‑free inference framework for Looped Transformers that reduces cross‑loop redundancy by employing token‑sparse updates, sparse attention, and KV‑residual quantization. It exploits observations that, as loops progress, state changes concentrate on a small token subset, attention differences are dominated by a sparse key subset, and KV residuals become amenable to low‑bit quantization. The method achieves lossless accuracy with up to 1.64× speedup and 6× KV‑cache memory reduction across several Looped Transformer models.
arXiv:2608. 13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications.
arXiv:2606. 16093v1 Announce Type: cross Abstract: Modeling long-range dependencies remains a central challenge in natural language processing.
arXiv:2608. 19920v1 Announce Type: new Abstract: A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive hardware budgets.
arXiv:2504. 17584v2 Announce Type: replace-cross Abstract: Attention-FC Disaggregated (AFD) LLM inference systems offload memory-bound Attention operations to memory-rich accelerators (e.
arXiv:2606. 09862v1 Announce Type: cross Abstract: The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios.
arXiv:2605.26797v2 Announce Type: replace Abstract: We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden...
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv:2609.25802v1 Announce Type: new Abstract: We introduce latest exact match attention (LEMA), an attention variant for transformers where queries and keys are binarized and each query attends onl...
arXiv:2511. 05313v2 Announce Type: replace Abstract: The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and linear attention.
arXiv:2502.09245v3 Announce Type: replace Abstract: In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standar...