Update pr-run-test.yml

Author: zhulinJulia24

.github/workflows/pr-run-test.yml

@@ -59,14 +59,14 @@ jobs:
           rjob submit --metadata-name=${{ env.JOB_NAME }} --charged-group=llmeval_gpu --private-machine=group --group=llmeval_gpu --namespace=ailab-llmeval --gpu=2 --cpu=32 --memory=32568 --private-machine=group --image=registry.h.pjlab.org.cn/ailab-puyu/xpuyu:torch-2.6.0-45d96d5f-0607 --env=COMPASS_DATA_CACHE=/mnt/shared-storage-user/auto-eval-pipeline/opencompass/llmeval/compass_data_cache --env=TIKTOKEN_CACHE_DIR=/mnt/shared-storage-user/auto-eval-pipeline/opencompass/llmeval/share_tiktoken --env=HF_ENDPOINT=https://hf-mirror.com --env=HF_DATASETS_CACHE=${{env.HF_DATASETS_CACHE}} --env=HF_HUB_CACHE=/mnt/shared-storage-user/large-model-center-share-weights/hf_hub --env=CUDA_MODULE_LOADING=EAGER --env=HF_DATASETS_OFFLINE=1 --env=TRANSFORMERS_OFFLINE=1 --env=HF_EVALUATE_OFFLINE=1 --env=HF_HUB_OFFLINE=1 --mount=gpfs://gpfs1/qa-llm-cicd:/mnt/shared-storage-user/qa-llm-cicd --mount=gpfs://gpfs1/opencompass-shared:/mnt/shared-storage-user/opencompass-shared --mount=gpfs://gpfs1/auto-eval-pipeline:/mnt/shared-storage-user/auto-eval-pipeline --mount=gpfs://gpfs1/large-model-center-share-weights:/mnt/shared-storage-user/large-model-center-share-weights -- bash -exc '/mnt/shared-storage-user/opencompass-shared/qa-llm-cicd/pr_test_new.sh ${{env.REPORT_ROOT}}/${{ github.run_id }}'
 
           for i in {1..300}; do
-            current_status=$(rjob get ${{ env.JOB_NAME }} | grep -oP 'rjob [^:]+: \K[^ ]+')
+            current_status=$(rjob get --namespace=ailab-llmeval ${{ env.JOB_NAME }} | grep -oP 'rjob [^:]+: \K[^ ]+')
             if [[ $current_status == "Succeeded" ]]; then
               echo "Task succeeded"
-              rjob logs job ${{ env.JOB_NAME }} -n 100
+              rjob logs job --namespace=ailab-llmeval ${{ env.JOB_NAME }} -n 100
               exit 0
             elif [[ $current_status == "Failed" || $current_status == "Stopped" ]]; then
               echo "Task failed or stopped, fetching logs"
-              rjob logs job ${{ env.JOB_NAME }} -n 100
+              rjob logs job --namespace=ailab-llmeval ${{ env.JOB_NAME }} -n 100
               exit 1
             fi
             sleep 6
@@ -101,7 +101,7 @@ jobs:
           conda activate ${{env.CONDA_ENV}}
           python3 -m pip uninstall opencompass -y
           conda info --envs
-          rjob stop job ${{ env.JOB_NAME }}
+          rjob stop job --namespace=ailab-llmeval ${{ env.JOB_NAME }}
 
   mock_api_test:
     runs-on: yidian_cu12
@@ -150,14 +150,14 @@ jobs:
           rjob submit --metadata-name=${{ env.JOB_NAME }} --charged-group=llmeval_gpu --private-machine=group --group=llmeval_gpu --namespace=ailab-llmeval --gpu=0 --cpu=${{ matrix.cpu }} --memory=${{ matrix.memory }} --private-machine=group --image=registry.h.pjlab.org.cn/ailab-puyu-puyu_gpu/lmdeploy:v0.12.0-cu12.8 --env=COMPASS_DATA_CACHE=/mnt/shared-storage-user/auto-eval-pipeline/opencompass/llmeval/compass_data_cache --env=TIKTOKEN_CACHE_DIR=/mnt/shared-storage-user/auto-eval-pipeline/opencompass/llmeval/share_tiktoken --env=HF_ENDPOINT=https://hf-mirror.com --env=HF_DATASETS_CACHE=${{env.HF_DATASETS_CACHE}} --env=HF_HUB_CACHE=/mnt/shared-storage-gpfs2/gpfs2-shared-public/huggingface/hub --env=CUDA_MODULE_LOADING=EAGER --env=HF_DATASETS_OFFLINE=1 --env=TRANSFORMERS_OFFLINE=1 --env=HF_EVALUATE_OFFLINE=1 --env=HF_HUB_OFFLINE=1 --env=REPORT_DIR=${{env.REPORT_ROOT}} --env=CHAT_TYPE=${{matrix.func_type}} --mount=gpfs://gpfs1/qa-llm-cicd:/mnt/shared-storage-user/qa-llm-cicd --mount=gpfs://gpfs1/opencompass-shared:/mnt/shared-storage-user/opencompass-shared --mount=gpfs://gpfs1/auto-eval-pipeline:/mnt/shared-storage-user/auto-eval-pipeline --mount=gpfs://gpfs2/gpfs2-shared-public:/mnt/shared-storage-gpfs2/gpfs2-shared-public -- bash -exc 'source ${{env.CONDA_PATH}}/bin/activate; conda activate ${{env.CONDA_ENV}}; conda env list; cd ${{github.workspace}}; ln -s /mnt/shared-storage-user/auto-eval-pipeline/opencompass/llmeval/compass_data_cache/data .; python /mnt/shared-storage-user/opencompass-shared/qa-llm-cicd/mock_chat_api.py --type winrate --port 26333 > mock_${{matrix.name}}.log 2>&1 & sleep 3; opencompass autotest/all/${{matrix.func_type}}.py --work-dir ${{env.REPORT_ROOT}}/${{ github.run_id }}/${{matrix.func_type}} --reuse;'
 
           for i in {1..300}; do
-            current_status=$(rjob get ${{ env.JOB_NAME }} | grep -oP 'rjob [^:]+: \K[^ ]+')
+            current_status=$(rjob get --namespace=ailab-llmeval ${{ env.JOB_NAME }} | grep -oP 'rjob [^:]+: \K[^ ]+')
             if [[ $current_status == "Succeeded" ]]; then
               echo "Task succeeded"
-              rjob logs job ${{ env.JOB_NAME }} -n 100
+              rjob logs job --namespace=ailab-llmeval ${{ env.JOB_NAME }} -n 100
               exit 0
             elif [[ $current_status == "Failed" || $current_status == "Stopped" ]]; then
               echo "Task failed or stopped, fetching logs"
-              rjob logs job ${{ env.JOB_NAME }} -n 100
+              rjob logs job --namespace=ailab-llmeval ${{ env.JOB_NAME }} -n 100
               exit 1
             fi
             sleep 6
@@ -192,4 +192,4 @@ jobs:
           conda activate ${{env.CONDA_ENV}}
           python3 -m pip uninstall opencompass -y
           conda info --envs
-          rjob stop job ${{ env.JOB_NAME }}
+          rjob stop job --namespace=ailab-llmeval ${{ env.JOB_NAME }}