Files
vllm-omni/docs/design/module/diffusion/diffusion_runtime.md
T
2026-08-10 19:25:03 +08:00

1.6 KiB

title, kind, status, owners, primary_code_paths, related_code_paths, depends_on, validation_paths, upstream_refs, last_reviewed
title kind status owners primary_code_paths related_code_paths depends_on validation_paths upstream_refs last_reviewed
Diffusion Runtime module draft
@Isotr0py
@princepride
@SamitHuang
@fhfuih
vllm_omni/diffusion/sched/**
vllm_omni/diffusion/executor/**
vllm_omni/diffusion/worker/**
vllm_omni/diffusion/hooks/**
vllm_omni/diffusion/postprocess/**
../engine_orchestration.md
../input_output_modality_contracts.md
diffusion_model_integration.md
tests/diffusion/diffusion_backend/**
tests/diffusion/hooks/**
diffusers.DiffusionPipeline
2026-07-16

Diffusion runtime

The diffusion runtime owns request admission, scheduling, execution, progress, output, cancellation, and cleanup inside a diffusion stage.

Candidate invariants

DIFF-RUNTIME-INV-001: One lifecycle owner

Rule: Every admitted request MUST have exactly one scheduler-owned lifecycle until completion, cancellation, or failure.

DIFF-RUNTIME-INV-002: Execution follows scheduler output

Rule: Executors and workers MUST execute scheduler decisions without admitting, reordering, or forwarding requests independently.

DIFF-RUNTIME-INV-003: Terminal cleanup is complete

Rule: Every terminal path MUST release request state, temporary tensors, hooks, and runtime-owned resources.

DIFF-RUNTIME-INV-004: Optional features use runtime hooks

Rule: Cache, profiling, offload, and parallel features SHOULD integrate at defined hooks instead of creating another request lifecycle.

Safe-change guide

Test success, cancellation, failure, shutdown, multiple requests, and resource cleanup.