Unverified50% confidenceBenchmarkExact time
When the cache roughly matches the index size, hot vector search p50 latency stays stable between 11 and 23 milliseconds.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedFor interactive search, P99 latency typically needs to be kept within a few hundred milliseconds.77% similarUnverifiedp50 latency refers to the duration of the request at the median when all requests are sorted by duration, with half the requests faster and half slower than that value.76% similarVerifiedIn testing, the p99 latency per 160-millisecond tick was 147.4–147.5 milliseconds, with zero missed deadlines across three rounds totaling 84,000 session ticks measured.72% similarUnverifiedSnapshot restoration time is now counted in the creation phase, and creation time has increased by about 50 milliseconds at p50; for uncached snapshots, the increase may be larger71% similarUnverifiedAplomb 1 对短问题的模型端计算时间约 15 毫秒,端到端延迟约 200 毫秒70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1136961API
curl https://kongchang.com/api/v1/knowledge/claims/1136961MCP
get_claim(id=1136961)