DeploymentConfig

from modal_training_gym.common.deployment import DeploymentConfig

Deploy a model behind a serving engine.

When recipe is None, defaults to SglangRecipe().

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
unauthenticated	bool	True

Methods

serve(self) -> "'ModelDeployment'"

Build, deploy, and return a ModelDeployment handle.

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
• GUI grounding with Qwen3-VL-8B — predict click coordinates from screenshots
• Cross-tokenizer agentic distillation on BFCL v3 multi-turn with live, execution-grounded rewards — DeepSeek V4 Flash teacher, Qwen3.6-35B-A3B student

Source: modal_training_gym/common/deployment.py