Unverified50% confidenceFactExact time
The L1 cache is a high-speed cache private to each SM, while the L2 cache is shared by all SMs.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
Unverified缓存层级通过L1/L2/L3多级缓存平衡访存速度与容量67% similarVerifiedThe disk caching mechanism persists already-computed KV Cache to storage media; when a subsequent request's prefix hits the cache, it can be reused directly, skipping redundant forward propagation.65% similarUnverifiedSM Occupancy refers to the ratio of the number of active warps per streaming multiprocessor to the maximum number of warps supported by the hardware.65% similarUnverifiedDouble buffering refers to the same data page existing simultaneously in both the OS page cache and shared buffers, resulting in duplicated memory usage and dilution of effective cache capacity.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084463API
curl https://kongchang.com/api/v1/knowledge/claims/1084463MCP
get_claim(id=1084463)