Albireo overlaps non-scalable overheads with compute in tensor-parallel LLM inference to raise the empirical optimal TP degree, delivering up to 1.9x throughput and 48% lower latency versus vLLM.
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
8 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
8
Pith papers citing it
1
external citations · Pith
abstract
While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and decoding stages. Recent works that compress KV caches with prefill acceleration reduce this cost but inadvertently tie the prefill compute reduction to the decoding KV budget. This coupling arises from overlooking the layer-dependent variation of critical context, often leading to accuracy degradation. To address this issue, we introduce FastKV, a KV cache compression framework designed to reduce latency in both prefill and decoding by leveraging the stabilization of token importance in later layers. FastKV performs full-context computation until a Token-Selective Propagation (TSP) layer, which forwards only the most informative tokens to subsequent layers. From these propagated tokens, FastKV independently selects salient KV entries for caching, thereby decoupling KV budget from the prefill compute reduction based on the TSP decision. This independent control of the TSP rate and KV retention rate enables flexible optimization of efficiency and accuracy. Experimental results show that FastKV achieves speedups of up to 1.82$\times$ in prefill and 2.87$\times$ in decoding compared to the full-context baseline, while matching the accuracy of the decoding-only baselines. Our code is available at https://github.com/dongwonjo/FastKV.
years
2026 8representative citing papers
OmniDrop is a training-free layer-wise token pruning framework for omni-modal LLMs that uses query guidance and temporal diversity to reduce prefill latency by up to 40% and memory by 14.7% while improving benchmark scores by up to 3.58 points.
SinkRouter identifies attention sinks as training-derived fixed points and routes around them to skip redundant KV-cache loads, delivering up to 2.03x decoding speedup on long-context benchmarks.
StructKV compresses LLM KV caches by tracking global in-degree centrality across network depth and dynamically selecting compression layers to preserve long-range dependencies better than local pruning methods.
HARD-KV bridges dynamic head-adaptive KV cache compression with static inference engine constraints via Cascade Cache and Logits Calibration, reporting up to 2x throughput gains on long-context math benchmarks.
InfoKV is an entropy-aware KV cache compression framework that integrates token-level predictive uncertainty and layer-wise representation evolution with attention scores to improve performance on long-context reasoning benchmarks.
AnchorKV augments KV cache compression with a soft penalty derived from a refusal anchor in key space to improve safety alignment against jailbreaks while preserving most utility.
MuKV adds multi-grained KV cache compression at patch-frame-segment levels plus semi-hierarchical retrieval to raise accuracy and cut memory in long video question-answering.
citing papers explorer
-
Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads
Albireo overlaps non-scalable overheads with compute in tensor-parallel LLM inference to raise the empirical optimal TP degree, delivering up to 1.9x throughput and 48% lower latency versus vLLM.
-
OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance
OmniDrop is a training-free layer-wise token pruning framework for omni-modal LLMs that uses query guidance and temporal diversity to reduce prefill latency by up to 40% and memory by 14.7% while improving benchmark scores by up to 3.58 points.
-
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
SinkRouter identifies attention sinks as training-derived fixed points and routes around them to skip redundant KV-cache loads, delivering up to 2.03x decoding speedup on long-context benchmarks.
-
StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
StructKV compresses LLM KV caches by tracking global in-degree centrality across network depth and dynamically selecting compression layers to preserve long-range dependencies better than local pruning methods.
-
HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
HARD-KV bridges dynamic head-adaptive KV cache compression with static inference engine constraints via Cascade Cache and Logits Calibration, reporting up to 2x throughput gains on long-context math benchmarks.
-
Information-Aware KV Cache Compression for Long Reasoning
InfoKV is an entropy-aware KV cache compression framework that integrates token-level predictive uncertainty and layer-wise representation evolution with attention scores to improve performance on long-context reasoning benchmarks.
-
AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor
AnchorKV augments KV cache compression with a soft penalty derived from a refusal anchor in key space to improve safety alignment against jailbreaks while preserving most utility.
-
MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
MuKV adds multi-grained KV cache compression at patch-frame-segment levels plus semi-hierarchical retrieval to raise accuracy and cut memory in long video question-answering.