from modal_training_gym.common.deployment import DeploymentConfigDeploy a model behind a serving engine.
Fields
Section titled “Fields”| Field | Type | Default | Description |
|---|---|---|---|
model | ModelConfig | ||
checkpoint | modal_training_gym.common.checkpoint.Checkpoint | None | None | |
recipe | VllmRecipe | SglangRecipe | None | None | |
app_name | str | None | None | |
served_model_name | str | None | None |
Methods
Section titled “Methods”serve(self) -> "'ModelDeployment'"
Section titled “serve(self) -> "'ModelDeployment'"”Build, deploy, and return a ModelDeployment handle.
Related Tutorials
Section titled “Related Tutorials”- Qwen3-4B haiku evaluation with verifiable rewards — serve, evaluate, train, compare
- Code RL with Harbor hello-world and sandboxed verification
- Multi-turn number-guessing RL with custom generate and reward functions
- On-policy distillation on math — Qwen3-8B teacher, Qwen3-4B student
- DAPO on math with Qwen3-4B
- Audio GRPO on Qwen3-ASR-1.7B — transcribe LibriSpeech, reward −WER