CPU and memory leak

[WhoIsDarth]

After running the service for a long time, I get a large number of running processes.

result: list[LMQLResult | str] = await lmql.run(
            prompt,
            model=model,
            output_writer=output_writer,
            **additional_context,
            **script_context,
        )
raw_response = result[0]

I am dynamically generate prompt scripts and pass them into lmql.run

[lbeurerkellner]

Thanks for reporting this. I will have to investigate a bit, to reproduce it well on my end.

As a workaround, depending on what you do, you could also just pass a prompt value as a parameter to a query that does not change over time (assuming you have no dynamic constraints).

[WhoIsDarth]

I do not control the format of the prompt, users send their prompts and I execute them

[iEgit]

seems to reproduce when it has long output (similar to the problem in https://github.com/eth-sri/lmql/issues/273) leading to errors and multiple retries of open ai due to extremely long context.