arXiv:2607. 15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.
arXiv:2607. 12550v1 Announce Type: new Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference.
arXiv:2607.12550v3 Announce Type: replace-cross Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference: it grows with batch size, context length, and depth, a...
The paper introduces LoopCD, a training‑free contrastive decoding framework that improves token selection in Loop‑Transformer models by comparing the final prediction with earlier recurrent passes. LoopCD operates either in logit space (LoopCD‑Logits) with a single extra output pass or in hidden‑state space (LoopCD‑Hidden) with no output overhead. Across multiple looped Transformer families, LoopCD yields significant performance gains—raising pass@1 scores on tasks such as AIME 2024 and HumanEval—while enabling a reduction in the number of recurrent loops and a corresponding decrease in inference FLOPs.
arXiv:2606. 18023v1 Announce Type: cross Abstract: Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count.
arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keepin...
arXiv:2602.08005v2 Announce Type: replace-cross Abstract: Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computati...
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standar...
arXiv:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
arXiv:2609.37988v1 Announce Type: new Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
The paper introduces JoLT, a training‑free compressor that jointly allocates rank and precision for key‑value (KV) cache compression in long‑context language models. JoLT treats grouped prefill caches as fourth‑order tensors, applies partial Tucker decomposition along token and feature modes, and uses a rotated low‑bit quantizer for residuals, all governed by a single Lagrangian dual under a global byte constraint. Across five models from four architecture families, JoLT achieves 2–3× compression with less than 0.2% perplexity loss, and near‑lossless retrieval accuracy on LLaMA‑3.1‑8B at 64K context up to 3× compression.
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...
The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.