> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# vLLM-Omni Configuration

The vLLM-Omni backend uses a dedicated entrypoint: `python -m dynamo.vllm.omni`. This page documents its CLI flags. For deployment guides and per-modality examples, see the [Diffusion Overview](/dynamo/dev/diffusion/overview).

These are the vLLM-Omni orchestration flags. The omni worker also accepts the same underlying vLLM engine arguments and the cross-cutting [Dynamo Runtime](/dynamo/dev/reference/components/runtime-configuration) flags (`--namespace`, `--endpoint`, and others).

## General Flags

**`--omni`** `flag`

Enable the vLLM-Omni orchestrator (required for all omni workloads).

---

**`--output-modalities`** `text | image | video | audio`

Output modality the worker registers endpoints for.

---

**`--stage-configs-path`** `path`

Path to stage config YAML (optional; vLLM-Omni uses model defaults if omitted).

---

**`--boundary-ratio`** `float` — default: 0.875

MoE expert switching boundary.

---

**`--flow-shift`** `float`

Scheduler flow\_shift (5.0 for 720p, 12.0 for 480p).

---

**`--default-video-fps`** `int` — default: 16

Default frames per second for generated videos.

---

## Memory & Performance

**`--vae-use-slicing`** `flag`

Enable VAE slicing for memory optimization.

---

**`--vae-use-tiling`** `flag`

Enable VAE tiling for memory optimization.

---

**`--enable-layerwise-offload`** `flag`

Enable layerwise offloading on DiT modules to reduce GPU memory.

---

**`--layerwise-num-gpu-layers`** `int` — default: 1

Number of ready layers to keep on GPU during generation.

---

**`--enforce-eager`** `flag`

Disable torch.compile for diffusion models.

---

**`--enable-cpu-offload`** `flag`

Enable CPU offloading for diffusion models.

---

## Diffusion Cache

**`--cache-backend`** `cache_dit | tea_cache`

Diffusion cache backend.

---

**`--cache-config`** `json`

Cache configuration as a JSON string (overrides defaults).

---

**`--enable-cache-dit-summary`** `flag`

Enable cache-dit summary logging after diffusion forward passes.

---

## Parallelism

**`--ulysses-degree`** `int` — default: 1

GPUs for Ulysses sequence parallelism in diffusion.

---

**`--ring-degree`** `int` — default: 1

GPUs for ring sequence parallelism in diffusion.

---

**`--cfg-parallel-size`** `int` — default: 1

GPUs for classifier-free guidance parallelism (1 or 2).

---

## Disaggregated Mode

See [vLLM-Omni Disaggregated Serving](/dynamo/dev/knowledge-base/modular-components/backends/v-llm/v-llm-omni-disaggregated-serving) for usage.

**`--stage-id`** `int`

Run as a single-stage worker for the given stage ID. Requires `--stage-configs-path`.

---

**`--omni-router`** `flag`

Run as the stage router. Requires `--stage-configs-path`. Mutually exclusive with `--stage-id`.

---

## Media Storage

**`--media-output-fs-url`** `url` — default: file:///tmp/dynamo\_media

Filesystem URL for storing generated media.

---

**`--media-output-http-url`** `url`

Base URL for rewriting media paths in responses (optional).

---