vllm_omni.host_weight_runtime.protocols ¶
Provider and consumer protocols for Host Weight Runtime extensions.
ArtifactWriter ¶
Bases: Protocol
open_tensor_file ¶
open_tensor_file(
relative_name: str,
specs: tuple[TensorWriteSpec, ...],
*,
ordered: bool = False,
) -> TensorFileWriter
BuildRequest dataclass ¶
CoordinationScope ¶
HostWeightStore ¶
Bases: Protocol
Exact artifact access whose deadlines bound lock acquisition only.
get_or_build ¶
get_or_build(
request: BuildRequest,
producer: WeightProducer,
*,
validation: ValidationLevel,
deadline: float,
) -> StoreResult
lookup ¶
lookup(
identity: WeightArtifactIdentity,
*,
validation: ValidationLevel,
deadline: float | None = None,
) -> StoreResult
LookupPhase ¶
ProductionMetadata dataclass ¶
format_metadata class-attribute instance-attribute ¶
format_metadata: CanonicalJson = field(
default_factory=CanonicalJson.empty
)
ProductionSourceMode ¶
RemoteArtifactDescriptor dataclass ¶
RemoteArtifactProvider ¶
Bases: Protocol
fetch ¶
fetch(
descriptor: RemoteArtifactDescriptor,
writer: ArtifactWriter,
) -> ProductionMetadata
TensorFileWriter ¶
TensorWriteSpec dataclass ¶
WeightProducer ¶
Bases: Protocol
Synchronous V1 producer; callers do not preempt an active build.
produce ¶
produce(writer: ArtifactWriter) -> ProductionMetadata
Produce one exact artifact synchronously or raise.
WeightProductionSpec dataclass ¶
coordination_scope class-attribute instance-attribute ¶
coordination_scope: CoordinationScope = (
CoordinationScope.SINGLE_PROCESS
)
lookup_phase class-attribute instance-attribute ¶
lookup_phase: LookupPhase = LookupPhase.PRE_LOAD_SAFE
WeightRestorePlan ¶
WeightRestorer ¶
Bases: Protocol
Validate a lease-to-model restore without mutating either input.
plan_restore ¶
plan_restore(
model: object, lease: HostWeightLease
) -> WeightRestorePlan
Return a validated plan; all model mutation is deferred to commit().