Unverified50% confidenceSolutionExact time
The model compresses the cache along three dimensions: 64 query heads share a single latent, every two adjacent tokens in the encoder are compressed into one entry, and only 4 out of 40 layers retain cache while the remaining 36 layers store nothing.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBase64 编码将每3字节二进制数据拆分为4组6位，输出长度约为原始数据的4/3倍72% similarVerifiedQuantized KV caches (such as storing KV vectors in FP8 or INT4) can compress the cache size to 1/2 or even 1/4 of the original.70% similarUnverifiedIn DeepSeek-V4.1-Flash, only four layers are responsible for writing the compressed KV, and the rest of the model shares this cache.70% similarUnverifiedCompressing child node indices from 64-bit pointers to 32-bit offsets both saves memory and allows a single 64-byte cache line to hold more index information.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923871API
curl https://kongchang.com/api/v1/knowledge/claims/923871MCP
get_claim(id=923871)