Models / inclusionAI
Ming-omni-tts-0.5B
serving recipe.
Ming-omni-tts-0.5B is a 0.5B dense model. vLLM publishes a tested serving recipe for it, and Wingsmith reads that recipe when you register the weights.
- Size
- 0.5BDense
- Context
- Not statedAs the recipe states it.
- Memory floor
- 16 GBSmallest published, whole replica.
- vLLM
- 0.22.0 or laterMinimum version in the recipe.
01 / Memory
Precisions and memory floors.
Each variant is a precision vLLM tested, sometimes published as its own repository.
| Variant | Precision | Memory floor | Weights |
|---|---|---|---|
| default | BF16 | 16 GB | inclusionAI/Ming-omni-tts-0.5B |
Floors are the minimum the vLLM recipe publishes across the whole replica, from vLLM's own runs. The control plane compares them with its own sizing from the model config.
02 / Parallelism
Layouts the recipe supports.
The recipe does not list parallelism strategies; its flags carry the tested layout.
03 / Hardware
Where vLLM ran it.
Node shapes the recipe reports an end-to-end run on.
The recipe does not mark any hardware as verified.
Wingsmith runs models through NVIDIA Dynamo, so it serves on NVIDIA GPUs. Other vendors are listed as the recipe states them.
04 / Flags
The tested baseline.
Base flags, then the default variant, then the features that are on by default, as the recipe composes them.
vllm serve inclusionAI/Ming-omni-tts-0.5B \
--omni \
--enforce-eagerDependencies
- vLLM-Omni provides the TTS serving backend and the `--omni` serve path. See the installation guide for pre-built wheels or building from source.
05 / Serve
Serve it with Wingsmith.
From a slug to an OpenAI-compatible endpoint, across your clusters.
Register the weights
In the console, or through the API. Resolving a slug proposes an artifact and writes nothing.
curl "http://localhost:8000/v1/artifacts/resolve?source=hf:inclusionAI/Ming-omni-tts-0.5B"Against the local control plane from the quickstart, where admin auth is off. Read the draft
The draft carries this recipe as upstream evidence: the tested flags, the precision and memory floor, the parallelism layouts, and the hardware vLLM verified, with links back to the recipe. Nothing from it is applied without you, and the draft warns when the plane's own sizing and the published floor differ by a quarter or more.
Create the workload
Choose the engine, device shape and scale. The plane picks the clusters, and each cluster's operator renders the deployment as a Dynamo graph.
Give it an endpoint
One model name for clients, routed by the gateway to deployments on every cluster serving it.
Questions
Common questions.
- How much GPU memory does Ming-omni-tts-0.5B need?The vLLM recipe publishes a minimum of 16 GB across the whole replica for its BF16 variant. That is vLLM's own measurement, not a per-GPU figure.
- Which parallelism layouts does the Ming-omni-tts-0.5B recipe support?The recipe does not list parallelism strategies.
- Can Wingsmith serve Ming-omni-tts-0.5B?Wingsmith serves models through NVIDIA Dynamo on clusters with NVIDIA GPUs. Register inclusionAI/Ming-omni-tts-0.5B and the plane attaches this vLLM recipe to the draft as evidence: its tested flags, precision and memory floor, for you to review rather than applied on your behalf. The recipe reports no end-to-end run on NVIDIA hardware.
From the vLLM recipe for inclusionAI/Ming-omni-tts-0.5B ↗ (snapshot at 4bcc189), Apache 2.0.
Status
Open source,
under Apache 2.0.
Wingsmith is pre-release. The first public release, and everything after it, will be under Apache 2.0.
Built and not built
Built
Multi-cluster placement and routing, Dynamo deployments, device inventory, endpoints and quotas, the console, the CLI, and three measurement tools.
Not built
Published images and charts, per-user roles and SSO, batch and training workloads, and a Helm chart for the control plane.
Pre-release. No tagged release, images, or charts yet, and APIs and protocols can change.