https://vlap.github.io/tags/workflow-optimization/Recent content in Workflow Optimization on Vladimir Lapinhttps://vlap.github.io/images/decor/vladimir_lapin.jpghttps://vlap.github.io/images/decor/vladimir_lapin.jpgHugoen-usMon, 20 Jul 2026 12:00:00 +0200https://vlap.github.io/posts/2026-07-20-scaling-python-hpc-uv-lustre/Mon, 20 Jul 2026 12:00:00 +0200https://vlap.github.io/posts/2026-07-20-scaling-python-hpc-uv-lustre/We’ve all watched a 64-node Slurm job stall for three minutes just importing xarray. Here is why standard Conda environments choke parallel filesystems like Lustre, and how pairing Astral uv with system LMOD modules eliminates job startup lag on MareNostrum 5.