implementation detail · filed under inference & serving
Max sequences tuning
A configuration detail that sets the maximum number of sequences to fit a target context length.
Also called Max sequences tuning for context fitting, --max-num-seqs 32.
- 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.
--max-num-seqs 32 — the single knob for fitting 1M context
usedinference servingin GLM-5.3vLLM
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 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 isolationPer-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