Regression runner on the server with pytest-xdist -n 14 (installed into ~/torchenv with Valeri's consent) and BLAS threads pinned to 1: 755 passed in 2:00 and 2:04, against 5:49 single-process on the server and 3:42 on the laptop. Single-process pytest on the server is slower than the laptop; the server only pays with parallelism.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

run_regression.sh

@@ -1,9 +1,14 @@
 #!/bin/bash
 # Frozen regression runner: detached, logged, with an explicit end marker, so an ssh
 # drop cannot kill it (2026-09-21: a foreground pytest over ssh died with the connection).
+#
+# -n 14 via pytest-xdist: single-process pytest on the server is SLOWER than the laptop
+# (5:49 against 3:42), so the server only pays with parallelism.  BLAS threads MUST be
+# pinned to 1, or every xdist worker grabs 3+ cores (2026-09-16: 50+ minutes, load 55/16).
+export OMP_NUM_THREADS=1 OPENBLAS_NUM_THREADS=1 MKL_NUM_THREADS=1
 cd "$HOME/sim-numerics" || exit 1
 for pass in 1 2; do
     echo "=== PASS $pass ==="
-    ~/torchenv/bin/python -m pytest tests -q -p no:cacheprovider 2>&1 | tail -4
+    ~/torchenv/bin/python -m pytest tests -q -p no:cacheprovider -n 14 2>&1 | tail -4
 done
 echo "=== REGRESSION DONE ==="