REVIEW 18 cited by
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
read the original abstract
With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for each token generation both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to speed up inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory consumption or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on a broad range of benchmarks, including RULER, LongBench, and Needle In A Haystack, and models like Llama-3.1-8B, Llama-3-8B-1M, GLM-4-9B-1M, Yi-9B-200K, Phi-3-Mini-128K, and Qwen2-7B-128K, we demonstrate that it can support up to 6$\times$ larger batch sizes and boost throughput by up to 3.04$\times$ on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory. The code is available at https://github.com/bytedance/ShadowKV.
Forward citations
Cited by 18 Pith papers
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
-
PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems
PrefixWall mitigates APC side channels in multi-tenant LLM systems via selective prefix isolation, delivering up to 70% higher cache reuse and 30% lower latency than full-isolation baselines.
-
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
KV-cache serving systems concentrate into five archetypes under a four-axis taxonomy, with ownership explaining residual distributed design variance and seven measurement gaps blocking next steps.
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents
Vortex provides a programmable frontend and backend for sparse attention in LLM serving, delivering up to 3.46x throughput over full attention while preserving accuracy.
-
Dynamic Short Convolutions Improve Transformers
Dynamic short convolutions applied to key/query/value projections and linear layers in Transformers yield consistent performance gains and 1.33-1.60x compute advantages over standard models on language modeling from 1...
-
Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI
MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
-
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
DashAttention introduces differentiable adaptive sparse hierarchical attention via α-entmax block selection, achieving full-attention accuracy at 75% sparsity with improved Pareto performance over NSA and InfLLMv2.
-
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.
-
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
-
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
A program-aware scheduler and tool-lifecycle manager for LLM agent workflows raises serving throughput by 1.5–3.6x and RL rollout throughput by 1.8–3.9x over vLLM/Continuum baselines.
-
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
HeteroCache dynamically allocates KV cache space to attention heads based on their temporal stability and uses hierarchical asynchronous retrieval to achieve state-of-the-art long-context performance with up to 3x fas...
-
OjaKV: Context-Aware Online Low-Rank KV Cache Compression
OjaKV introduces hybrid full-rank storage for key tokens combined with online low-rank KV cache compression via Oja's algorithm to support memory-efficient long-context LLM inference.
-
Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding
PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.
-
An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
Fluxion achieves 1.5x-3.7x speedup in long-context LLM inference with CPU KV caches while limiting accuracy degradation to at most 0.26 relative to full attention.
-
DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
DVSA combines bidirectional attention, MI-based contrastive learning, and dynamic label disambiguation to improve zero-shot learning performance under ambiguous (noisy) labels.
-
DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
DeInfer adds multiple optimizations to improve parallel inference speed for decomposed LLMs while remaining compatible with existing techniques.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.