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.
SQuat: Subspace-orthogonal kv cache quantization.arXiv preprint arXiv:2503.24358, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
InnerQ delivers 1.3x average speedup over prior KV cache quantization and 2.7x over baseline by inner-dimension grouping, hybrid symmetric/asymmetric quantization, high-precision windows for recent and sink tokens, and prefold per-channel key normalization.
citing papers explorer
-
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.
-
InnerQ: Hardware-Aware Tuning-Free Quantization of KV Cache for Large Language Models
InnerQ delivers 1.3x average speedup over prior KV cache quantization and 2.7x over baseline by inner-dimension grouping, hybrid symmetric/asymmetric quantization, high-precision windows for recent and sink tokens, and prefold per-channel key normalization.