Unverified50% confidenceFactExact time
AttSVD is a training-free KV cache compression scheme that performs low-rank compression of the KV cache along the feature axis via attention-guided SVD.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSVD is the mathematical core of PCA dimensionality reduction, recommender system matrix factorization, and the LoRA low-rank adaptation fine-tuning method.69% similarUnverifiedLoRA（Low-Rank Adaptation）的核心思想是利用 SVD 的低秩近似原理，将大模型微调成本压缩至可在消费级 GPU 上运行的规模66% similarVerifiedSVD (Singular Value Decomposition) can decompose any matrix into the product of three matrices, and is the mathematical foundation of matrix factorization in recommender systems, image compression, and Latent Semantic Analysis (LSA).61% similarUnverifiedDnR FlatPic's original PNG-to-SVG functionality was based on VTracer version 1.0.0-alpha.3, called via Node/WASM.58% similarUnverifiedv0.30.0 simplifies the execution flow related to KDA, AttnRes, and MLA, and adds MXFP8 KV cache and asynchronous Engram mechanisms for some models.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983251API
curl https://kongchang.com/api/v1/knowledge/claims/983251MCP
get_claim(id=983251)