From ebac7291466de88b009844a347ebc19308099913 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Thu, 16 Apr 2026 13:05:48 -0700 Subject: [PATCH] [Infra] CI: reduce llm_translation_testing parallelism and tolerate worker restarts Workers in llm_translation_testing have been crashing mid-run with "Not properly terminated" (OOM), even after bumping resource_class to xlarge. Reduce xdist workers from 8 to 4 to lower peak memory, and add --max-worker-restart=5 so a crashed worker is replaced instead of failing the whole run. --- .circleci/config.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.circleci/config.yml b/.circleci/config.yml index 60246ef786c..6238339b5a7 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -682,7 +682,7 @@ jobs: for dir in "${IGNORE_DIRS[@]}"; do IGNORE_ARGS="$IGNORE_ARGS --ignore=$dir" done - uv run --no-sync python -m pytest -v tests/llm_translation $IGNORE_ARGS --junitxml=test-results/junit.xml --durations=20 -n 8 --timeout=120 --timeout_method=thread --retries 2 --retry-delay 5 + uv run --no-sync python -m pytest -v tests/llm_translation $IGNORE_ARGS --junitxml=test-results/junit.xml --durations=20 -n 4 --timeout=120 --timeout_method=thread --retries 2 --retry-delay 5 --max-worker-restart=5 no_output_timeout: 15m # Store test results