REVIEW 7 cited by
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
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
Signed reviews
abstract
Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the compute and memory operation cost of self-attention can be optimized by using the probability that multiple LLM requests have shared system prompts in prefixes. In this paper, we introduce ChunkAttention, a prefix-aware self-attention module that can detect matching prompt prefixes across multiple requests and share their key/value tensors in memory at runtime to improve the memory utilization of KV cache. This is achieved by breaking monolithic key/value tensors into smaller chunks and structuring them into the auxiliary prefix tree. Consequently, on top of the prefix-tree based KV cache, we design an efficient self-attention kernel, where a two-phase partition algorithm is implemented to improve the data locality during self-attention computation in the presence of shared system prompts. Experiments show that ChunkAttention can speed up the self-attention kernel by 3.2-4.8$\times$ compared to the state-of-the-art implementation, with the length of the system prompt ranging from 1024 to 4096.
Forward citations
Cited by 7 Pith papers
-
MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
Region-labeled tokens in LLM agent traces have order-of-magnitude different attention lifetimes, and a decay-plus-pinning eviction policy preserves system facts under fixed KV budgets while recency collapses as context grows.
-
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
Lexico compresses LLM key-value caches by replacing each cached vector with a sparse combination of about 4,000 shared dictionary atoms, keeping 90-95% of accuracy at 15-25% of the cache memory.
-
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
A timing side-channel on shared LLM caches can partially reconstruct private user inputs in prompt-engineering and RAG services.
-
CoDec: Prefix-Shared Decoding Kernel for LLMs
CoDec combines KV-cache reads across requests that share a prefix, yielding average 1.9x decode-attention speedup and 120.9x less global memory traffic versus FlashDecoding.
-
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
The authors propose episodic memory, with five defining properties, as the unifying framework needed for LLM agents to learn and remember over long time horizons.
-
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
DAM derives per-layer and per-head attention masks from a calibration dataset and extrapolates them to long inputs, matching full-attention retrieval accuracy while reducing memory and compute.
-
A Survey on Large Language Model Acceleration based on KV Cache Management
A survey that classifies KV cache management techniques for faster LLM inference into token-level, model-level, and system-level categories, with benchmark resources.
Discussion (0). Continue with ORCID to comment.