Skip to main content Crate inferlab_protocol Copy item path Source AdapterError A structured rejection an integration returns in an AdapterResponse::Error AdapterProtocol The schema root aggregating every wire type. It exists to generate one
committed JSON schema (and the Python SDK models); its optional client
fields are never all populated in a single message. BenchCaseInput A single Bench case: its load shape and the number of requests to send. BenchClientRequest The request the Bench measurement runtime passes to its client: the
endpoint, model, bench definition, the load case to run, and the artifact
directory. BenchClientResult The result a Bench client writes for the measurement runtime to consume. BenchDatasetCatalogInput Immutable release-catalog facts resolved by the Rust control plane. BenchDatasetPreparationRequest The bounded tokenizer-backed operation that materializes one dataset
population before any Bench case starts. BenchDatasetPreparationResult Terminal result of dataset population materialization. BenchDefinitionInput The workload shape a Bench client drives, shared across its load cases. BenchPopulationInput One frozen dataset population consumed sequentially by every Bench case. BenchRequestSloInput Per-request latency bounds lowered to the release-owned Bench runner. BenchRequestSloResult File-bound request-SLO evidence derived from AIPerf profiling records. BenchTokenCountSummary Summary of the realized token counts. Exact per-entry values remain in the
population evidence artifact. CaptureControlRequirement The HTTP paths a capture target exposes to open and close a capture window. CaptureTargetRequirement Marks a replica as a profiling capture target and carries its window
control ([[RFC-0004:C-WORKLOAD-PROFILING]]). ClientEndpointInput The public workload endpoint an Eval or Bench client connects to. EndpointAssignment A concrete host/port endpoint the control plane allocated for a process. EndpointRequirement The workload endpoint’s protocol and named OpenAI paths, plus an optional
prefix-cache-reset action a Bench case can invoke between runs. EvalClientRequest The request the Eval measurement runtime passes to its client: the endpoint
to hit, the model, the eval definition, and where to write artifacts. EvalClientResult The result an Eval client writes for the measurement runtime to consume. EvalMetricGate The effective threshold comparison for the configured primary metric. EvalNormalizedMetric One finite lm-eval metric with its exact native provenance. EvalTrialSummary Reconstructible aggregate counts for fixed outer Eval trials. HttpActionSpec An HTTP action (method and path) invoked against the workload endpoint. HttpTargetRegistryReadiness The integration-owned HTTP registry contract for target-aware readiness. IntegrationIdentity The integration’s identity recorded on its results: adapter id, adapter
version, and the framework it lowers to. LaunchFileDeclaration One immutable text input a rendered process requires before it can launch. MeasurementModelInput The model identity used by measurement clients. Unlike integration
planning, a benchmark client may need a controller-visible tokenizer
locator. Parallelism Framework-neutral component-aware parallelism ([[RFC-0003:C-SERVE-PARALLELISM]]).
Every component is optional so an operator can override one without
repeating the rest; omitted components are filled by the integration into a
complete effective shape. ParallelismAttention Attention-block parallelism: tensor, data, and context degrees. ParallelismExperts MoE expert parallelism: tensor, data, expert, and dense-tensor degrees. ParallelismOuter Outer deployment parallelism: tensor and pipeline degrees. PlanServeInput The requested serve shape a PlanServe operation lowers into a topology. PlanServeResult The lowered topology returned by a PlanServe: the effective server-level
shape, per-role resolution, whole-replica requirements, role links, and the
public and per-role endpoint requirements the control plane then allocates. ProcessSpec A launchable process: its argument vector and environment. RawArtifact A raw output file a client produced, retained as workload evidence. RenderInputDeclaration One workspace-authored UTF-8 source file an integration declares during
planning for the control plane to supply during final rendering. RenderServeInput The planned topology plus the control plane’s concrete allocations that a
RenderServe operation turns into final process invocations. RenderServeResult The final process invocations returned by a RenderServe, one per supplied
allocation. RenderedServeProcess A rendered process bound to the allocation id it was produced for. ServeModelInput The logical model supplied during serving planning and rendering. ServeProcessAllocation One concrete process the control plane placed, supplied to RenderServe:
its identity, rank, machine, devices, model locator, and allocated
endpoints and named ports. ServeReplicaRequirement A whole-replica resource and readiness requirement the integration declares
without choosing placement, ranks, or concrete endpoints. ServeRoleInput A requested serving role: its identity, kind, replica cardinality, and
declared (not-yet-completed) parallelism and settings. ServeRoleResult A role as the integration resolved it: preserved identity and cardinality
with the complete effective settings and parallelism. SuppliedRenderInput The original declared path plus the exact UTF-8 contents and digest the
control plane supplies to an integration during final rendering. AdapterErrorCode Machine-readable failure category an adapter reports in an AdapterError AdapterRequest The one JSON request an integration reads from stdin, tagged by the
requested operation. AdapterResponse The one JSON response an integration writes to stdout, tagged by outcome. AdapterResult The successful result of an AdapterRequest AllocationLaunch The machine-local launch channel selected by the control plane. BenchDatasetCacheState Read-only cache state observed while resolving the Bench plan. BenchDatasetInput Release-qualified public Bench datasets. BenchLoadInput How a Bench case paces its requests. BenchRequestSourceInput One closed request origin lowered by Inferlab for the Bench runtime. BuiltinRouterKind An Inferlab-owned routing implementation with stable target semantics. ClientStatus The terminal outcome a measurement client reports. EndpointProtocol The application protocol a workload endpoint speaks. EvalDefinitionInput The measurement an Eval client runs against the workload endpoint. EvalFailureKind A typed Eval failure category preserved across the client boundary. EvalMetricComparison The threshold comparison selected from lm-eval’s scoring direction. EvalMetricGateConclusion The terminal conclusion of an lm-eval metric threshold gate. EvalTaskSourceInput The resolved lm-eval task source consumed by the release-owned Eval runner. HttpMethod The HTTP method of an HttpActionSpec KvTransferMechanism The KV-transfer mechanism connecting prefill and decode. ProtocolVersion The shared protocol version used by framework integrations and release-owned
measurement clients. The only accepted value is 6 (serialized as the
string "6"); a mismatch is rejected before lowering. ReadinessProbe How the control plane decides a process is ready. RoutingResult The closed routing owner selected during integration planning. ServeRoleKind The logical role a replica plays in a serve topology. ServeRoleLink A directed link between serve roles the integration declares as part of the
topology. ServeTopology The serving deployment topology. SettingValue A framework-specific server setting value carried as structured JSON data
(never a pre-rendered shell fragment) across the integration boundary. TargetEndpointScheme The application protocol used to identify serving targets in a registry. PROTOCOL_SCHEMA_ID protocol_schema