arXiv AI
Kwai Summary Attention V2 Technical Report
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 13
Kwai Summary Attention V2 Technical Report
The paper introduces Kwai Summary Attention V2, an improved version of the KSA architecture that compresses distant context into learnable summary tokens per chunk. It addresses bottlenecks of the original hybrid KSA‑Full design by allowing flexible KV cache compression across layers and reducing computation costs in full‑attention layers. The new approach treats summary tokens as both KV memory and sparse indexers, enhancing efficiency.
arXiv Computation and Language
Sep 4
SGD-KV: Summarization Guided KV Cache Compression
SGD-KV is a head‑aware framework for compressing key‑value caches in large language models. It uses a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation, allowing the KV cache budget to be allocated based on each head’s summarization score. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B show state‑of‑the‑art performance on up to 1M‑token contexts while cutting KV cache memory usage by up to 75%.
arXiv AI
Jul 7
Kwai Summary Attention Technical Report
arXiv:2604. 24432v2 Announce Type: replace-cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system.
Hugging Face Trending Papers
Sep 3
SGD-KV: Summarization Guided KV Cache Compression
SGD-KV is a head‑aware framework that compresses key‑value caches in large language models by using a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation. It prioritizes these heads during compression, achieving state‑of‑the‑art performance on long‑context benchmarks with up to 1M tokens while cutting KV cache memory usage by as much as 75%. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B confirm that allocating cache budget based on summarization scores yields a superior efficiency‑accuracy trade‑off for long‑context inference.
arXiv AI
Jul 21
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
arXiv Machine Learning
Jun 5
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.