Unverified50% confidenceFactExact time
Linear attention models (such as Mamba and RWKV) need only maintain a fixed-size recurrent state at inference time rather than caching the entire history of key-value pairs, so memory usage is independent of sequence length.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMamba's memory footprint during inference remains constant and does not grow linearly with sequence length, narrowing the gap with Transformers on language modeling tasks.77% similarUnverifiedRWKV is an architecture that replaces the attention mechanism with a linear recurrence formula, resulting in memory usage during inference that remains constant rather than growing linearly with sequence length.76% similarUnverifiedIn large language model inference, KV-Cache is used to store the key-value pairs already computed in the attention mechanism, thereby avoiding repeated computation.73% similarVerifiedState space models (SSMs) such as Mamba abandon the attention mechanism and use recurrent structures to achieve linear time complexity sequence modeling.73% similarUnverifiedLoRA推理时可将BA与原权重合并，不增加任何推理延迟，通常只应用于注意力层的Q、V权重矩阵72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084562API
curl https://kongchang.com/api/v1/knowledge/claims/1084562MCP
get_claim(id=1084562)