Unverified50% confidenceFactExact time
For multi-turn conversations or long-document question answering, if the KV of the entire context is recomputed on every request, the compute overhead grows quadratically with context length.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge models are stateless; in multi-turn conversations the client must resend the complete history of messages with each request, causing the input length of the Nth turn to be roughly the accumulation of all messages from the previous N-1 turns, so input cost grows quadratically with the number of turns.71% similarUnverifiedThe longer the context, the more VRAM and computational overhead grow approximately quadratically with length.71% similarUnverifiedThe KV cache grows linearly with context length, increasing the memory read volume per step in the decoding phase, which is the fundamental reason decoding speed decreases as context grows.70% similarUnverifiedUnder a linear conversation structure, token consumption is cumulative—every request requires retransmitting the entire history, increasing inference latency and driving up API call costs.70% similarUnverifiedInputs of different lengths within a batch need to be padded to a uniform length, which introduces additional computational overhead.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1031675API
curl https://kongchang.com/api/v1/knowledge/claims/1031675MCP
get_claim(id=1031675)