REVIEW 27 cited by
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
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
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
read the original abstract
Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly dynamic behavior of the attention layers, showcasing significant differences in computational characteristics and memory requirements from the non-attention layers. This presents substantial challenges for resource management and performance optimization in service systems. Existing static model parallelism and resource allocation strategies fall short when dealing with this dynamicity. To address the issue, we propose Infinite-LLM, a novel LLM serving system designed to effectively handle dynamic context lengths. Infinite-LLM disaggregates attention layers from an LLM's inference process, facilitating flexible and independent resource scheduling that optimizes computational performance and enhances memory utilization jointly. By leveraging a pooled GPU memory strategy across a cluster, Infinite-LLM not only significantly boosts system throughput but also supports extensive context lengths. Evaluated on a dataset with context lengths ranging from a few to 2000K tokens across a cluster with 32 A100 GPUs, Infinite-LLM demonstrates throughput improvement of 1.35-3.4x compared to state-of-the-art methods, enabling efficient and elastic LLM deployment.
Forward citations
Cited by 27 Pith papers
-
Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG
SpliceLeak is the first end-to-end side-channel attack on non-prefix KV cache in RAG, using Step-Wave timing leaks to fingerprint private prompt lengths and extract tokens with up to 100% success using 63 requests per...
-
Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
On a real multi-node H100 cluster the authors show that for MLA, routing the ~1 KB compressed query row is cheaper than moving cache chunks and supply a topology-aware cost model accurate to ~7% on IBGDA fabrics.
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
A bit-slice-based accelerator (MCBP) jointly reduces GEMM computation, weight traffic, and KV cache traffic for LLM inference, claiming 9.43x speedup and 31.1x energy efficiency over A100.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
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.
-
C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
C2KV trains a sidecar extractor to produce compressed, position-agnostic KV cache segments that can be concatenated at inference time, reducing prefill, storage, and memory-bandwidth costs without modifying the frozen...
-
Auto-Scaling Heterogeneous Neural Processing Units for Energy and Cost-Efficient LLM Serving
NeuScale routes LLM inference requests to the most energy/cost-efficient configuration of heterogeneous NPU chips using roofline allocation and runtime auto-scaling.
-
ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill
ASAP is a disaggregated asynchronous inference system for the prefill phase of MoE models that removes DP-EP synchronization barriers and reports 90% higher SLO-compliant throughput than synchronous baselines.
-
StickyInvoc: Rethinking Task Models for High-throughput Workflows in the LLM Era
StickyInvoc introduces sticky tasks that load LLM model state once and invocation tasks that reuse it, yielding 3.6x speedup on a 150k-inference workflow.
-
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.
-
NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding
NanoCP introduces request-level dynamic context parallelism to decouple MoE communication from KV cache placement in hybrid data-expert parallel serving, reporting up to 3.27x higher request rates and 2.12x lower P99 ...
-
MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
MoE-Hub enables seamless MoE communication overlap via hardware-accelerated destination-agnostic data transmission, delivering 1.40x-3.08x per-layer and 1.21x-1.98x end-to-end speedups over prior systems.
-
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
SPIN co-designs sparse attention with hierarchical memory to achieve 1.66-5.66x higher throughput, 7-9x lower TTFT, and up to 58% lower TPOT than vLLM and original sparse implementations.
-
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
AMMA is a memory-centric multi-chiplet architecture using HBM-PNM cubes, custom logic dies, hybrid parallelism, and reordered collectives that delivers 15.5X lower attention latency and 6.9X lower energy than NVIDIA H...
-
Topology-Aware Data Movement for Disaggregated GPU Inference
TopKV claims topology-aware KV cache transfer can cut disaggregated inference latency by 3–18x, but the projected figures are undermined by inconsistent bandwidth values and a circular validation approach.
-
WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
WarmServe reduces tail TTFT by up to 50.8× versus autoscaling and supports 2.5× higher throughput than GPU-sharing by using one-for-many prewarming, model placement, KV cache reservation, and efficient tensor switching.
-
Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
Amoeba adaptively adjusts tensor parallelism at runtime for LLM inference services to handle mixed short and long context requests, delivering 1.75x-6.57x throughput gains over prior solutions in real-world trace evaluations.
-
Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism
Hetis dynamically splits LLM attention across heterogeneous GPUs at the granularity of individual heads while keeping dense computation on a selected subset, and reports up to 2.25x throughput gains over Splitwise and Hexgen.
-
Lizard: An Efficient Linearization Framework for Large Language Models
Lizard linearizes Transformer LLMs via subquadratic attention and adaptive learnable modules, recovering near-original performance while outperforming prior linearization methods on MMLU and associative recall.
-
MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training
MegaScale-Data is a distributed data loading system that disaggregates preprocessing and applies auto-partitioning to deliver 4.5x higher end-to-end training throughput and 13.5x lower CPU memory usage for multisource...
-
Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference
Omni-Flow introduces a three-layer abstraction (Control Flow, Data Flow, Compute Flow) for unified orchestration and KV cache sharing in multimodal inference pipelines.
-
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding
KernelFlume presents a disaggregated decode architecture that separates core attention from projection/FFN paths to enable elastic scaling of attention nodes, reporting up to 61% lower cost per million tokens versus f...
-
Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference
A unified KV cache system with architecture-specific sizing, six-tier memory from GPU to filesystems, and Bayesian prediction delivers 7.4x higher batch sizes, 70-84% hit rates, and projected 1.7-2.9x throughput gains.
-
ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators
ODMA raises KV-cache utilization by up to 19.25% and throughput by 23-27% on Cambricon MLU accelerators by dynamically adjusting prediction buckets and using a safety pool for LLM serving.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
-
Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies
The paper surveys and taxonomizes inference optimization methods for large vision-language models across four categories while noting limitations and open problems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.