Filippo Luca Ferretti

By default, the installation of JAX comes with the CPU version of `jaxlib`. If you're interested in the GPU version, I'd suggest to install it as per the [JAX documentation](https://jax.readthedocs.io/en/latest/installation.html#pip-installation-gpu-cuda-installed-via-pip-easier)...

I was thinking of using something that leverages `functools.total_ordering` for the comparison operators. We could also use `jax_dataclasses.pytree_dataclass` to maintain immutability as follows: ```python @jax_dataclasses.pytree_dataclass @total_ordering class Time: nanoseconds: jnp.int64...

Thanks Diego, I'll take a look at it! It would probably be a good idea to also add that check in the tests

Thanks @traversaro! I will address your comments one-by-one in future commits

More resources: - [`jax.experimental.sparse`](https://jax.readthedocs.io/en/latest/jax.experimental.sparse.html) module - https://github.com/google/jax/issues/19212 - [`jax.scipy.sparse.linalg.cg`](https://jax.readthedocs.io/en/latest/_autosummary/jax.scipy.sparse.linalg.cg.html)

WIP at https://github.com/ami-iit/jaxsim/tree/feature/mass_inverse_rbd

Doing some additional tests, I found out that a similar problem is raised. This time, it seems to be related to the integrators: ```py Traceback (most recent call last): File...

After some testing, I found out that the objects `data.state.physics_model` are not compatible. Moreover, when `data` is created for a model without joints, like in the example in https://github.com/ami-iit/jaxsim/issues/103#issuecomment-2058752595, the...

Furthermore, I believe that we should pay attention to the `dynamics` attribute of `Integrator`, which being just a Protocol, it cannot be compared with `==`

Thanks a lot @xela-95 for the PR! Could you please explain how did you get the errors using the `vmap`? It would be nice to be able to reproduce and...