implementation detail · filed under inference & serving
Composite-key sorting for topology-aware GPU rank assignment
A topology-aware placement detail that sorts bundle indices by domain minimum topology rank, topology rank, and GPU ID.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
bundle indices are sorted by a( domain_min_topo_rank,topo_rank,gpu_id )composite key
usedsoftware implementationin NeMo-RLNVIDIA
Filed alongside
Other methods under inference & serving :: inference scheduling.
Asynchronous schedulingNUMA binding of workers to GPU-local CPU socketsContinuous batchingCross-group pinning of cache-hit blocksDual-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