← 研踪 PaperTrailarXiv:2605.17757 · v2
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
首次提交 2026-05-18 10:24
版本更新 2026-11-11 07:07
雷达观测 2026-11-13 11:12
摘要
INT2 KV-cache quantization is attractive for long-context LLM serving, yet making it both accurate and practical remains challenging. Data-oblivious rotations such as Hadamard transforms flatten channel outliers, but still degrade sharply at INT2 because they ignore how downstream attention queries the cache. We propose OSCAR, an ultra-low-bit KV-cache quantization method that estimates attention-aware covariance targets offline and uses them to derive fixed per-layer rotations and clipping thresholds. By aligning the quantization basis with the second-moment structures consumed by attention, OSCAR preserves attention fidelity at 2-bit precision. Beyond theoretical analysis under a frozen-error surrogate, we build a serving-ready OSCAR system with fused Triton write and decode kernels that preserve paged KV-cache layouts and prefix caching, integrating into modern serving engines such as SGLang and vLLM. We evaluate OSCAR on reasoning and coding benchmarks with generation traces of up to 32K tokens across five tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR narrows the BF16 accuracy gap to 3.78 and 1.21 points, respectively, where Hadamard-only INT2 collapses, and matches BF16 within run-to-run variance on Qwen3-32B and GLM-4.7 (358B parameters). On RULER-NIAH up to 128K tokens, OSCAR substantially outperforms QuaRot-style INT2 across context lengths. System-wise, OSCAR compresses KV-cache memory by nearly $8\times$, boosts multi-request throughput by up to $7.8\times$ at large batch sizes within the same memory budget, and accelerates batch-size-1 decoding by up to $3.1\times$ over BF16 by cutting KV memory traffic.
作者备注：46 pages, 10 figures. v2 adds matched-baseline comparisons, residual diagnostics, and expanded long-context analysis
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-11 07:07 · 最新观测版本
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
INT2 KV-cache quantization is attractive for long-context LLM serving, yet making it both accurate and practical remains challenging. Data-oblivious rotations such as Hadamard transforms flatten channel outliers, but still degrade sharply at INT2 because they ignore how downstream attention queries the cache. We propose OSCAR, an ultra-low-bit KV-cache quantization method that estimates attention-aware covariance targets offline and uses them to derive fixed per-layer rotations and clipping thresholds. By aligning the quantization basis with the second-moment structures consumed by attention, OSCAR preserves attention fidelity at 2-bit precision. Beyond theoretical analysis under a frozen-error surrogate, we build a serving-ready OSCAR system with fused Triton write and decode kernels that preserve paged KV-cache layouts and prefix caching, integrating into modern serving engines such as SGLang and vLLM. We evaluate OSCAR on reasoning and coding benchmarks with generation traces of up to 32K tokens across five tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR narrows the BF16 accuracy gap to 3.78 and 1.21 points, respectively, where Hadamard-only INT2 collapses, and matches BF16 within run-to-run variance on Qwen3-32B and GLM-4.7 (358B parameters). On RULER-NIAH up to 128K tokens, OSCAR substantially outperforms QuaRot-style INT2 across context lengths. System-wise, OSCAR compresses KV-cache memory by nearly $8\times$, boosts multi-request throughput by up to $7.8\times$ at large batch sizes within the same memory budget, and accelerates batch-size-1 decoding by up to $3.1\times$ over BF16 by cutting KV memory traffic.
查看此版本解读 →查看此版本原文 ↗