Pystan on py 3.9, asyncio error

I updated my system to a new python version 3.9 and hence also reinstalled latest pystan. I was using pystan2 before. I know get this error I never saw before. Any ideas?

Found model in cache. Done.
Traceback (most recent call last):
  File "/home/dnachbar/python/...", line 35, in <module>
    fit = model.sample(num_samples=1000, num_chains=2)
  File "/home/dnachbar/.local/lib/python3.9/site-packages/stan/", line 74, in sample
    return self.hmc_nuts_diag_e_adapt(**kwargs)
  File "/home/dnachbar/.local/lib/python3.9/site-packages/stan/", line 94, in hmc_nuts_diag_e_adapt
    return self._create_fit(kwargs)
  File "/home/dnachbar/.local/lib/python3.9/site-packages/stan/", line 279, in _create_fit
  File "/usr/lib/python3.9/asyncio/", line 44, in run
    return loop.run_until_complete(main)
  File "/usr/lib/python3.9/asyncio/", line 642, in run_until_complete
    return future.result()
  File "/home/dnachbar/.local/lib/python3.9/site-packages/stan/", line 209, in go
    raise RuntimeError(operation["result"]["message"])
RuntimeError: Exception during call to services function: `ValueError('Initialization failed.')`, traceback: `['  File "/home/dnachbar/.local/lib/python3.9/site-packages/httpstan/", line 153, in call\n    future.result()\n']`

pystan should do a better job of displaying the error message. The relevant error is “Initialization failed.”.

It could be a problem with your Stan model. Stan is having a hard time finding a good place to start sampling from.

Oh ok, it did work before properly, maybe I need to scale my input data better. Let me try