arXiv:2608.30386v1 Announce Type: cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substa...
arXiv:2608. 15533v1 Announce Type: cross Abstract: Linear attention models eliminate the quadratic prefix computation and context-growing KV cache of softmax attention by replacing pairwise token interactions with recurrent state updates.
arXiv:2607. 07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context.
arXiv:2608. 02032v1 Announce Type: new Abstract: Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures.
Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attention memories, while recurrent models such as state space models (SSMs) and linear attention maintain compact recurrent states.
arXiv:2607. 02805v1 Announce Type: cross Abstract: High-throughput long-context generation is one of the central challenges for large language models.
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...
HARTS (Hybrid‑Attention RL over Tree Structures) is a new system that jointly plans microbatches, data‑parallel replica assignments, and microbatch‑slot schedules to efficiently train agentic reinforcement learning models with hybrid attention over arbitrary rollout trees. It uses prefix compression and a linear‑time algorithm for chunkwise linear attention to avoid recomputing shared prefixes, enabling activation recomputation and bounded state replay while preserving trajectory‑wise training benefits. In experiments on an Agentic RL workload derived from SWE‑bench tasks, HARTS delivers 4.81–4.87× speedups in forward, backward, and gradient computations across multiple parallel configurations, with numerical differences comparable to baseline self‑rerun variation and a similar reward trend over the first 120 training steps.
The paper introduces ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs). ACache identifies a small set of critical affix tokens, called Anchor Tokens, and selectively recomputes their key-value states while reusing the rest of the affix cache. Experiments on Fast-dLLM and Nano-vLLM show that recomputing about 20% of affix tokens restores accuracy and can reduce recompute latency by up to 55.7% while improving throughput by up to 1.68×.
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:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
arXiv:2606. 16093v1 Announce Type: cross Abstract: Modeling long-range dependencies remains a central challenge in natural language processing.