REVIEW 11 cited by
PyramidInfer: Pyramid KV Cache Compression for High-throughput 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
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
read the original abstract
Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store computed keys and values (KV cache) in the GPU memory. Existing methods study the KV cache compression to reduce memory by pruning the pre-computed KV cache. However, they neglect the inter-layer dependency between layers and huge memory consumption in pre-computation. To explore these deficiencies, we find that the number of crucial keys and values that influence future generations decreases layer by layer and we can extract them by the consistency in attention weights. Based on the findings, we propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer saves significant memory by computing fewer keys and values without sacrificing performance. Experimental results show PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache.
Forward citations
Cited by 11 Pith papers
-
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
Sparse prefix caching via dynamic programming for optimal checkpoint placement under overlap distributions improves the Pareto frontier for recurrent and hybrid LLM serving on shared-prefix data.
-
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation...
-
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.
-
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
EntropyInfer adaptively allocates inference compute using per-head attention entropy for rigid/dynamic classification during prefilling and compresses KV cache with generated tokens, achieving up to 2.39x speedup on l...
-
ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
ProactiveLLM enables active interaction in streaming LLMs by learning semantic sufficiency cues from partial inputs through mask-based modeling and synchronized privileged self-distillation without external supervision.
-
ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
ReST-KV formulates KV eviction as layer-wise output reconstruction optimization with spatial-temporal smoothing, outperforming baselines by 2.58% on LongBench and 15.2% on RULER while cutting decoding latency by 10.61...
-
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
-
LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
LightTransfer identifies lazy layers in LLMs like LLaMA and replaces their attention with streaming attention to form hybrid models, delivering up to 2.17x throughput with under 1.5% drop on LongBench and strong resul...
-
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
PyramidKV dynamically compresses KV cache across layers following pyramidal information funneling, matching full performance at 12% retention and outperforming alternatives at 0.7% retention with up to 20.5 accuracy gains.
-
ClusterFusion++: Expanding Cluster-Level Fusion to Full Transformer-Block Decoding
ClusterFusion++ fuses the entire Transformer block (LayerNorm to residual) via CUDA extensions and achieves 1.34x throughput on Pythia-2.8B with near-identical output fidelity.
-
Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction
Structural protection of boundary tokens in globally capped KV cache eviction recovers 69-90% of full-cache quality at 13% retention and dominates differences among scoring policies.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.