AI Dynamo#

This workload (test_template_name is AIDynamo) runs AI inference benchmarks using the Dynamo framework with distributed prefill and decode workers.

Usage Example#

See Running AI Dynamo with CloudAI for details.

API Documentation#

Command Arguments#

class cloudai.workloads.ai_dynamo.ai_dynamo.AIDynamoCmdArgs(
*,
docker_image_url: str,
huggingface_home_host_path: Path = PosixPath('/home/runner/.cache/huggingface'),
huggingface_home_container_path: Path = PosixPath('/root/.cache/huggingface'),
dynamo: AIDynamoArgs,
genai_perf: GenAIPerfArgs,
run_script: str = '',
**extra_data: Any,
)[source]#

Bases: CmdArgs

Arguments for AI Dynamo.

docker_image_url: str#
huggingface_home_host_path: Path#
huggingface_home_container_path: Path#
dynamo: AIDynamoArgs#
genai_perf: GenAIPerfArgs#
run_script: str#

Test Definition#

class cloudai.workloads.ai_dynamo.ai_dynamo.AIDynamoTestDefinition(*, name: str, description: str, test_template_name: str, cmd_args: ~cloudai.workloads.ai_dynamo.ai_dynamo.AIDynamoCmdArgs, extra_env_vars: dict[str, str | ~typing.List[str]] = {}, extra_cmd_args: dict[str, str] = {}, extra_container_mounts: list[str] = [], git_repos: list[~cloudai._core.installables.GitRepo] = [], nsys: ~cloudai.models.workload.NsysConfiguration | None = None, predictor: ~cloudai.models.workload.PredictorConfig | None = None, agent: str = 'grid_search', agent_steps: int = 1, agent_metrics: list[str] = ['default'], agent_reward_function: str = 'inverse', script: ~cloudai._core.installables.File = File(src=PosixPath('/home/runner/work/cloudai/cloudai/src/cloudai/workloads/ai_dynamo/ai_dynamo.sh')), dynamo_repo: ~cloudai._core.installables.GitRepo = GitRepo(url=https://github.com/ai-dynamo/dynamo.git, commit=f7e468c7e8ff0d1426db987564e60572167e8464))[source]#

Bases: TestDefinition

Test definition for AI Dynamo.

cmd_args: AIDynamoCmdArgs#
script: File#
dynamo_repo: GitRepo#
property docker_image: DockerImage#
property installables: list[Installable]#
property huggingface_home_host_path: Path#