arXiv AI
Aug 11
Full-bandwidth transformer
arXiv:2608. 08888v1 Announce Type: new Abstract: Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth.
FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates
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.
Related stories
arXiv Machine Learning
Sep 16
LLM Inference in a Flash!
The paper "LLM Inference in a Flash!" proposes an integer‑only quantization scheme and a dictionary‑based KV cache compression technique to enable large language model inference on compute‑in‑flash (CIF) devices. By eliminating floating‑point operations and reducing KV cache traffic through sparse dictionary coding, the authors achieve minimal accuracy loss while cutting dynamic KV cache traffic by 15× on Llama‑3.1‑8B and Qwen‑2.5‑7B models.
arXiv Machine Learning
Jul 31
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.
arXiv Machine Learning
Jul 3
Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
arXiv Machine Learning
Sep 2
Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
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 AI
Sep 15
T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic Routing
arXiv:2609.15160v1 Announce Type: new Abstract: Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across mul...
arXiv AI
Jun 9
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
arXiv:2606. 09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving.
arXiv Machine Learning
Jul 3
Hyperloop Transformers
arXiv:2604. 21254v3 Announce Type: replace Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets.
arXiv AI
Jul 28
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
arXiv:2605. 09877v4 Announce Type: replace-cross Abstract: Recall presents a difficult choice: transformers have a linearly growing memory that slows each successive token, while linear RNNs typically have fixed costs but limited recall.
arXiv Machine Learning
Jul 15
AVQ-Attention: Adaptive Vector-Quantized Attention
arXiv:2607. 12789v1 Announce Type: new Abstract: The $\mathcal{O}(N^2)$ complexity of attention over $N$ tokens remains a computational bottleneck in transformer models.
arXiv Machine Learning
Aug 20
FlashAttention for Scalable Vector Architectures
FlashAttention-V is a blocked FlashAttention implementation optimized for scalable vector architectures, designed to reduce the memory bandwidth bottleneck of transformer attention on CPUs. By fusing operations, exploiting parallelism across attention heads, and inter‑head packing, it improves vector register utilization and memory locality, enabling efficient scaling from short to very long vectors. Benchmarks on TinyLlama, Llama 3.2, Qwen2.5, and Pythia‑410M show 22×–42× speedups over scalar FlashAttention in prefill and 8×–11× in decode on a Banana Pi BPI‑F3, while also revealing quantization‑related bottlenecks that limit long‑vector scalability.
arXiv Computation and Language
Aug 21
Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
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.