vllm_omni.clients.utils ¶
Client-local helpers for duplex JSON metric blocks.
STREAMING_OUTPUT_UNIT_TYPES module-attribute ¶
STREAMING_OUTPUT_UNIT_TYPES = frozenset(
{"text", "stream", "audio"}
)
StageModalityFlags ¶
distribution_summary ¶
distribution_summary(
values: Sequence[float], *, digits: int = 3
) -> dict[str, float | int] | None
Summarize values as {count, mean, p50, p99} for duplex report fields.
metric_mean ¶
Read a scalar mean, or the mean field of a distribution summary.
stage_modality_flags ¶
stage_modality_flags(
final_output_type: object, output_unit_type: object
) -> StageModalityFlags
Classify a stage from wire final_output_type / output_unit_type.
summarize_stage_metrics ¶
summarize_stage_metrics(
request_metrics: Sequence[Mapping[str, object]],
) -> dict[str, dict[str, object]] | None
Roll per-response engine stage blocks into {count, mean, p50, p99}.
Reads stages when present, otherwise stage0_tokens as stage "0". Zero or missing tpot_ms / tpop_ms values are omitted, matching session tpot_ms.