Unverified50% confidenceTradeoffExact time
This article chose HPA rather than VPA because the memory limit of a single Worker determines that it can only hold a fixed number of Actors; enlarging a single Worker's memory cannot solve the scheduling bottleneck, and increasing the number of Workers is the correct scaling direction.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHPA deals with increases and decreases in the number of horizontal replicas, whereas VPA (Vertical Pod Autoscaler) adjusts the resource quota of a single Pod.67% similarUnverifiedParallel architectures should calculate the required number of Workers based on P95 latency rather than average latency during capacity planning.56% similarUnverifiedHPA supports setting minReplicas and maxReplicas to bound scaling, avoiding unbounded growth or scaling to zero.55% similarUnverifiedOn UMA, the so-called 'on CPU' weights are actually sitting in the same unified RAM that the GPU also needs, and moving a tensor from MPS to CPU does not reduce overall memory pressure, only changes the access path and the state of the pages.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1035018API
curl https://kongchang.com/api/v1/knowledge/claims/1035018MCP
get_claim(id=1035018)