jolly-florist-66728
11/12/2024, 2:42 PM@dynamic
def my_dynamic_wf():
results = []
...
Create some chunks of task inputs
...
for c in chunks:
# Answer
It seems like you're experiencing serialization of map_tasks
that were previously running in parallel. This could be due to changes in the Flyte version or configuration settings that affect task execution. According to Flyte Discussion on Dynamic Workflows, map_task
does not support dynamic workflows in the same way as regular tasks, which might lead to unexpected behavior like serialization.
Would you like more details on potential causes or solutions for this issue?
Sources:
- Flyte Discussion on Dynamic Workflows
Slack Link
https://.slack.com/archives/CP2HDHKE1/p1731422521.168569 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.