@ancient-wolf-19325 Is there a way to limit the number of executions that run at the same time?

Yes, Flyte allows you to limit the number of concurrent executions using the

max_parallelism

setting. This can be configured at the platform level, per launch plan, or per execution. 1. Platform Default: Set a platform-wide default for maximum parallelism. 2. Launch Plan: Override the default for a specific launch plan using

flytekit.LaunchPlan.get_or_create()

. 3. Execution: Override the default for a specific execution using

pyflyte run --max-parallelism

or by setting it in the UI.

from flytekit import LaunchPlan

LaunchPlan.get_or_create(
    name="my_cron_scheduled_lp",
    workflow=my_workflow,
    max_parallelism=10,
)

For more details, refer to the Flyte documentation. Would you like more detail on any specific method? Sources: - Flyte Documentation on Concurrency vs Parallelism 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.

@ancient-wolf-19325 Is it possible to limit the number of workflows running at the same time?

Yes, it is possible to limit the number of workflows running concurrently in Flyte. This can be achieved by setting the

max_parallelism

attribute at the workflow level. This attribute limits the number of parallel tasks within a workflow execution.

from flytekit import LaunchPlan

LaunchPlan.get_or_create(
    name="my_workflow_lp",
    workflow=my_workflow,
    max_parallelism=10,
)

Additionally, you can configure this setting at the platform level or for specific executions. For more details, refer to the Flyte documentation. Would you like more detail on configuring this for specific executions or at the platform level? Sources: - Flyte Documentation on Concurrency vs Parallelism 👍 0 button 👎 1 button 💡 Hint: Mention @ancient-wolf-19325 in the thread for followups.