NaN in DPMSolverMultistepInverseScheduler

Hi, everyone, I'm new to diffusers. I'm trying to use DPMSolverMultistepInverseScheduler for DDIM inversion. The applied config is:
```python
dpmpp_2m_sde_karras_scheduler_inv = DPMSolverMultistepInverseScheduler(
num_train_timesteps=1000,
beta_start=0.00085,
beta_end=0.012,
algorithm_type="sde-dpmsolver++",
use_karras_sigmas=True,
steps_offset=1
)
```
And the DDIM inversion is realized through:
```python
self.scheduler.set_timesteps(self.inv_config.steps)
timesteps = self.scheduler.timesteps
with torch.autocast(device_type=self.device, dtype=self.dtype):
for i, t in enumerate(tqdm(timesteps)):
noises = []
x_index = torch.arange(len(x))
batches = x_index.split(self.batch_size, dim = 0)
for batch in batches:
noise = self.pred_noise(
x[batch], conds, timesteps[i], concat_conds=x[batch], batch_idx=batch)
noises += [noise]
noises = torch.cat(noises)

x = self.scheduler.step(noises, t, x, generator=self.rng, return_dict=False)[0]
```
But NaN occurs in the first scheduler step. I dug into it and found it happens in `dpm_solver_first_order_update`:
https://github.com/huggingface/diffusers/blob/560fb5f4d65b8593c13e4be50a59b1fd9c2d9992/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L627-L633
The self.sigmas is `tensor([ 0.0292, 0.0462, 0.0710, 0.1065, 0.1563, 0.2249, 0.3178, 0.4417,
0.6050, 0.8176, 1.0911, 1.4396, 1.8795, 2.4300, 3.1132, 3.9548,
4.9844, 6.2356, 7.7471, 9.5622, 11.7303, 14.3068, 17.3539, 20.9411,
25.1461, 25.1461])`. Its increasing order leads `lambda_t ` to be smaller than `lambda_s` and therefore a negative `h`.
As a result, in https://github.com/huggingface/diffusers/blob/560fb5f4d65b8593c13e4be50a59b1fd9c2d9992/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py#L638-L644
`torch.sqrt(1.0 - torch.exp(-2 * h))` becomes NaN. But I noticed that in `DPMSolverMultistepScheduler`, the problem is avoided by applying flip:
https://github.com/huggingface/diffusers/blob/560fb5f4d65b8593c13e4be50a59b1fd9c2d9992/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L395-L396
I've searched for many usage examples, but I still can't figure out the stem of the problem. Can anybody give a help?🙏