REVIEW 30 cited by
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
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
read the original abstract
Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound problem, significantly constraining the system throughput. Existing methods rely on dropping unimportant tokens or quantizing all entries uniformly. Such methods, however, often incur high approximation errors to represent the compressed matrices. The autoregressive decoding process further compounds the error of each step, resulting in critical deviation in model generation and deterioration of performance. To tackle this challenge, we propose GEAR, an efficient KV cache compression framework that achieves near-lossless high-ratio compression. GEAR first applies quantization to majority of entries of similar magnitudes to ultra-low precision. It then employs a low rank matrix to approximate the quantization error, and a sparse matrix to remedy individual errors from outlier entries. By adeptly integrating three techniques, GEAR is able to fully exploit their synergistic potentials. Our experiments demonstrate that compared to alternatives, GEAR achieves near-lossless 4-bit KV cache compression with up to 2.38x throughput improvement, while reducing peak-memory size up to 2.29x. Our code is publicly available at https://github.com/HaoKang-Timmy/GEAR.
Forward citations
Cited by 30 Pith papers
-
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
HeadQ removes 84-94% of excess perplexity from 2-bit key quantization by storing low-rank residuals in a calibration-learned query basis for score-space correction and using A²-weighted distortion for values.
-
RoPE-Aware Bit Allocation for KV-Cache Quantization
Block-GTQ performs RoPE-aware greedy bit allocation on KV caches using per-block energy scores, cutting logit MAE 32-80% versus uniform TQ-MSE and lifting long-context task scores substantially at 2-3 bits per dimension.
-
HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling
HACK++ is a head-aware KV cache compression framework for VAR models that decouples current-scale attention from historical cache under adaptive per-head budgets to achieve near-lossless generation at 30% attention an...
-
FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
FibQuant is a universal fixed-rate vector quantizer for KV-cache compression that uses a radial-angular codebook matched to the spherical-Beta source after Haar rotation and strictly outperforms scalar quantization at...
-
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.
-
MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression
MosaicKV achieves up to 16x attention speedup, 4.8x lower decode latency, 7.3x higher throughput, and 3x memory reduction with 1.76% accuracy loss via dynamic two-D KV cache compression and management on H800 GPUs.
-
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
CompressKV uses Semantic Retrieval Heads to guide KV-cache token selection and layer-wise budget allocation, retaining over 97% performance with 3% cache on LongBench QA tasks.
-
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
Kamera stores a low-rank patch with each position-free KV chunk to restore cross-chunk conditioning lost in naive reuse, enabling cheap reordering, sliding windows, and recall across attention mechanisms.
-
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
IntentKV prunes KV cache using cross-turn intent memory and attention scoring, achieving up to 77.8% reduction in worst-case peak tokens and 92.6% in KV reads at 8k budget with negligible accuracy drop on Qwen models.
-
Cartridges at Scale: Training Modular KV Caches over Large Document Collections
CAS trains composable per-document KV cache cartridges via dynamic distractor mixing and a rotating budget manager, scaling to million-token collections with 10-31 point gains over monolithic cartridges and matching R...
-
SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference
SPARQLe is a hardware-software co-design that splits quantized activations into dense low bits and sparse high bits to run inference on narrower datapaths while claiming to preserve full-precision accuracy.
-
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
OSCAR achieves near-BF16 accuracy for 2-bit KV cache quantization by using offline spectral covariance-aware rotations aligned with attention, plus a custom deployable INT2 kernel compatible with paged serving.
-
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.
-
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Spherical KV introduces angle-domain attention with spherical key parameterization and rate-distortion retention to cut KV cache residency while preserving efficient paged decoding.
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
HeadQ reduces 84-94% of excess perplexity in 2-bit key quantization by adding low-rank logit corrections in a calibration-learned query basis, with further gains from an A^2-weighted value policy.
-
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Token-wise INT4 KV-cache quantization plus block-diagonal Hadamard rotation recovers nearly all accuracy lost by naive INT4 while adding zero end-to-end overhead under paged serving constraints.
-
Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
-
Quantization Dominates Rank Reduction for KV-Cache Compression
Quantization of the KV cache beats rank reduction for matched storage budgets by 4-364 PPL, because dimension removal can flip attention token selection under softmax while bounded quantization noise usually preserves...
-
eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization
eOptShrinkQ compresses KV caches to ~2.2 bits per entry via optimal spectral shrinkage and quantization, outperforming prior methods on LongBench while matching FP16 on multi-needle retrieval.
-
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
AdaHOP applies pattern-aware Hadamard transforms and selective outlier extraction to enable from-scratch MXFP4 training of LLMs at BF16 quality with up to 3.6X memory compression and 1.46X speedup.
-
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Quant VideoGen reduces KV cache memory by up to 7 times in autoregressive video diffusion models via semantic aware smoothing and progressive residual quantization, achieving better quality than baselines with under 4...
-
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a fac...
-
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
LogQuant applies log-based filtering for 2-bit KV cache quantization in LLMs, claiming 25% higher throughput, 60% larger batches, and 40-200% accuracy gains on math/code tasks versus existing compression approaches.
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
-
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
HeadQ applies score-space logit corrections for keys and attention-weighted surrogates for values to KV-cache quantization, removing 84-94% of excess perplexity in 2-bit key experiments across six models.
-
LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind
TurboMind delivers up to 61% lower latency and 156% higher throughput for mixed-precision LLM inference across 16 models and 4 GPU architectures via optimized weight packing, adaptive alignment, instruction parallelis...
-
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
A survey organizing serving-time KV cache optimization techniques into temporal, spatial, and structural system behaviors, analyzing cross-behavior co-design patterns and open challenges.
-
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
VECTOR augments eviction-based KV cache compression with three-way token routing that combines importance scoring and offline regression-based reconstructability estimation to improve quality at high compression ratios.
-
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.