New RunLLM response generated: >>>*# Question* Hi...
# runllm-flyte-trial
j
New RunLLM response generated: >>>*# Question* Hi folks.. Question about map_tasks. I have a dynamic which triggers 2 map_tasks (same task really but to handle the fan out which is more than 5k). Earlier I would see both trigger simultaneously but in my most recent run I saw them getting serialized despite no dependency between them. Code looks like this:
Copy code
@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.