Jack S. Baker

A CVXPY layer handling a quadratic problem can only deal with positive definite Q-matrices

2

Looking at: https://locuslab.github.io/2019-10-28-cvxpylayers/, scroll down to the heading "The OptNet QP". You will see it is suggested that a QP is handled like: ```python n, m, p = 10, 5,...

Demonstrate parallel execution of a loss function

3

On an HPC cluster, each term in a mean square loss can be calculated using embarrassingly parallel logic. Unfortunately, the native way of doing this with `jax` (using `jax.vmap` and...

The advantage of implementing stresses is similar to that of forces (see #96 ), but applied to periodic systems. Much like for forces, these can be implemented by autodiff or...

Implementing ionic forces in Grad DFT would be useful as this provides information beyond the total energy and density for training neural functionals. There is potential here to strongly improve...

Grad DFT **is not** intended as a general purpose high performance DFT code. Its domain of applicability is for training neural functionals. Accordingly, if we wish to perform production level...

The return of the NaN

8

I've noticed that for a few basis sets, NaN gradients are appearing again when trained using the DIIS SCF loops but not the linear mixing loops. I think this is...

Implement a limited number of high priority unit tests

2

There are presently no unit tests at all in the repo. It is very likely that we will not have time to achieve high test coverage, but we should identify...

Allow certain exit codes at user's discretion

6

### What should we add? For a number of reasons, some code you are running with `srun` may exit with an exit code other than 0 (0 indicates "success", non-zero...

Slurm electrons fails when called within a Dask sublattice which itself is called in a Dask lattice.

2

### Environment - **Covalent version**: 0.220 - **Covalent-Slurm plugin version**: 0.16.0 - **Python version**: 3.8.16 - **Operating system**: MacOS Ventura 13.3.1 ### What is happening? When running a slurm electron...

Reconnect SSH after disconnect

1

This PR implements feature request #64 . When in _poll_slurm, we now do two things: 1. When `get_status` is called, any `conn.run()` commands are run through a new method `run_remote_command_with_reconnect`....