vLLM v0.8.5 · Version scoped

Scheduler token budget

seed slicenot evaluated at v0.8.5legacy evidence: v0.4.2legacy evidence: main-2026-07-21evidence: source code and documentation

Coverage for how vLLM represents and constrains max_num_batched_tokens in scheduler iteration token budgets.

Strong for the seeded v0.4.2 defaults and constraints; partial for latest-docs behavior and broader tuning.

This topic is intentionally scoped to promoted max_num_batched_tokens evidence, not all scheduler token-budget behavior.

Schema has not evaluated this topic at the selected version.

0 claims0 history facts0/2 entities

No claims at this version scope.

Runtime observations for real workloads are not represented in this seed corpus.

Schema.ai can cite docs and code defaults, but should not claim measured throughput or latency outcomes.

Check: Add runtime benchmark or incident evidence before serving workload-specific performance conclusions.

Coverage is limited to v0.4.2 source/docs and a latest-docs snapshot.

Schema.ai should not infer behavior for unobserved intermediate or future releases.

Check: Promote additional tagged source snapshots before broadening version applicability.