diff --git a/docs/HPC.md b/docs/HPC.md index f33d512..ff18a5f 100644 --- a/docs/HPC.md +++ b/docs/HPC.md @@ -74,25 +74,6 @@ After installation, run these commands to ensure your environment is set up corr python -c "import torch, jax; print(f'GPU: {torch.cuda.is_available()}'); print(f'JAX: {jax.devices()}')" ``` -## PR Verification (Quick Start) - -If you are a reviewer verifying a PR, run this single block: - -```bash -git checkout -module swap cluster/donphan -qsub -I -l nodes=1:gpus=1 - -# Inside the interactive session: -cd "$PBS_O_WORKDIR" -bash scripts/hpc/install.sh -python -c "import torch, jax; print(torch.cuda.is_available()); print(jax.devices())" -exit - -# Verify batch submission -qsub scripts/hpc/train.pbs -``` - ## Managing Dependencies `env/hpc/requirements.txt` is auto-generated from `pyproject.toml`. To regenerate: diff --git a/scripts/hpc/install.sh b/scripts/hpc/install.sh index 8a625a9..d1b69db 100644 --- a/scripts/hpc/install.sh +++ b/scripts/hpc/install.sh @@ -19,6 +19,8 @@ if [ -n "$PBS_O_WORKDIR" ]; then cd "$PBS_O_WORKDIR" fi +mkdir "${PBS_O_WORKDIR}/runs" + # Mirror configs to $VSC_DATA to avoid home quota limits (3GB) # vsc-venv manages environments relative to the requirements file PROJ_NAME=$(basename "$PWD") diff --git a/scripts/hpc/train.pbs b/scripts/hpc/train.pbs index a5d7a9d..3d53193 100644 --- a/scripts/hpc/train.pbs +++ b/scripts/hpc/train.pbs @@ -6,6 +6,8 @@ #PBS -N brittlestar-ppo #PBS -l nodes=1:ppn=8 #PBS -l walltime=24:00:00 +#PBS -o runs/brittlestar-ppo.o$PBS_JOBID +#PBS -e runs/brittlestar-ppo.e$PBS_JOBID set -euo pipefail