implementation detail · filed under inference & serving
Cross-group pinning of cache-hit blocks
A cache-consistency detail that pins each hit block across all groups before allocation.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
every hit block is therefore pinned across all groups before anything is allocated.
coreinference servingin Kimi K3Moonshot AI
Filed alongside
Other methods under inference & serving :: inference scheduling.
Asynchronous schedulingNUMA binding of workers to GPU-local CPU socketsComposite-key sorting for topology-aware GPU rank assignmentContinuous batchingDual-cluster consistent-hash failover for cache affinityEnvoy-based proxy with custom orchestratorExacto routingGreedy feasible-rank placement by remaining capacityHost-side scheduling optimizationIncreasing batch size for inferenceLatency-sensitive execution class with priority isolationMax sequences tuningPer-node hard admission constraintPrefix-cache-aware session affinity schedulingRegistering NVLink domains as Ray custom resourcesRequest-class resource-budget admission controlRuntime-signal-based rollout concurrency auto-throttlingSub-NUMA partitioning with per-VM NUMA bindingWorkload-aware routed-expert GEMM scheduling