STAR-KV applies differentiable soft thresholding for per-head and per-block adaptive low-rank KV cache compression, combined with hybrid decomposition and low-rank-aware quantization, achieving up to 75% compression and 3.1x throughput gains.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
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.
OVQ-attention delivers linear-time constant-memory sequence mixing via sparse Gaussian-mixture-based memory updates, matching self-attention performance on tasks up to 64k length while using far less memory.
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% latency overhead.
EVA is a vector-quantization hardware architecture that transforms LLM decoding from GEMV to GEMM via direct codebook dot products and conflict-free output buffering, claiming up to 11.17x speedup over prior lookup designs.
citing papers explorer
-
STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
STAR-KV applies differentiable soft thresholding for per-head and per-block adaptive low-rank KV cache compression, combined with hybrid decomposition and low-rank-aware quantization, achieving up to 75% compression and 3.1x throughput gains.
-
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.
-
Online Vector Quantized Attention
OVQ-attention delivers linear-time constant-memory sequence mixing via sparse Gaussian-mixture-based memory updates, matching self-attention performance on tasks up to 64k length while using far less memory.
-
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% latency overhead.
-
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
EVA is a vector-quantization hardware architecture that transforms LLM decoding from GEMV to GEMM via direct codebook dot products and conflict-free output buffering, claiming up to 11.17x speedup over prior lookup designs.