TriAttention compresses KV cache by exploiting stable pre-RoPE Q/K concentration and trigonometric distance preferences to match full-attention reasoning accuracy with far lower memory and higher speed.
Gqa: Training generalized multi-query transformer models from multi-head check- points
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CSAttention precomputes fixed-size query-centric lookup tables in offline prefill to enable fast table-lookup decoding, delivering near-identical accuracy to full attention and up to 4.6x speedup at 95% sparsity for 32K-128K contexts.
citing papers explorer
-
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
TriAttention compresses KV cache by exploiting stable pre-RoPE Q/K concentration and trigonometric distance preferences to match full-attention reasoning accuracy with far lower memory and higher speed.
-
CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference
CSAttention precomputes fixed-size query-centric lookup tables in offline prefill to enable fast table-lookup decoding, delivering near-identical accuracy to full attention and up to 4.6x speedup at 95% sparsity for 32K-128K contexts.