vllm - 💡(How to fix) Fix [Bug] API hangs/deadlocks when requesting logprobs on multi-node Ray deployment (PP=2, TP=8) [1 participants]

2026-03-31 10:51:51  Total Usage:
2026-03-31 10:51:51   0.0/336.0 CPU
2026-03-31 10:51:51   0.0/16.0 GPU
2026-03-31 10:51:51   0B/3.23TiB memory
2026-03-31 10:51:51   0B/372.53GiB object_store_memory
2026-03-31 10:51:51  
2026-03-31 10:51:51  From request_resources:
2026-03-31 10:51:51   (none)
2026-03-31 10:51:51  Pending Demands:
2026-03-31 10:51:51   (no resource demands)
2026-03-31 10:51:51  ==========================================
2026-03-31 10:51:51  + echo ==========================================
2026-03-31 10:51:51  ++ cat
2026-03-31 10:51:51  + USER_COMMAND='#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py'
2026-03-31 10:51:51  ++ cat
2026-03-31 10:51:51  + RUNTIME_ENV='{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}'
2026-03-31 10:51:51  + '[' -n '#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py' ']'
2026-03-31 10:51:51  Ray cluster is ready. Submitting user command as a job...
2026-03-31 10:51:51  + echo 'Ray cluster is ready. Submitting user command as a job...'
2026-03-31 10:51:51  ++ date +%s
2026-03-31 10:51:51  + JOB_ID=raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:51  Submitting job with ID: raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:51  + echo 'Submitting job with ID: raysubmit-1774925511-jo-dcq42sipnlhjwfx4'
2026-03-31 10:51:51  + RAY_ADDRESS=http://127.0.0.1:8265
2026-03-31 10:51:51  + set +e
2026-03-31 10:51:51  + '[' -n '{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}' ']'
2026-03-31 10:51:51  + ray job submit --address http://127.0.0.1:8265 --submission-id raysubmit-1774925511-jo-dcq42sipnlhjwfx4 --runtime-env-json '{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}' -- bash -lc '#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py'
2026-03-31 10:51:52  2026-03-31 10:51:52,906	INFO cli.py:41 -- Job submission server address: http://127.0.0.1:8265
2026-03-31 10:51:53  2026-03-31 10:51:53,101	INFO dashboard_sdk.py:338 -- Uploading package gcs://_ray_pkg_af2613c049db5f5c.zip.
2026-03-31 10:51:53  2026-03-31 10:51:53,102	INFO packaging.py:588 -- Creating a file package for local module '/mnt/c20250204_hs/jyq/deepseek'.
2026-03-31 10:51:53  2026-03-31 10:51:53,337	INFO job_manager.py:568 -- Runtime env is setting up.
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:65 -- ---------------------------------------------------------------------
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:66 -- Job 'raysubmit-1774925511-jo-dcq42sipnlhjwfx4' submitted successfully
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:67 -- ---------------------------------------------------------------------
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:291 -- Next steps
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:292 -- Query the logs of the job:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:294 -- ray job logs raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:296 -- Query the status of the job:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:298 -- ray job status raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:300 -- Request the job to be stopped:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:302 -- ray job stop raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,474	INFO cli.py:312 -- Tailing logs until the job exits (disable with --no-wait):
2026-03-31 10:52:14  bash: /mnt/c20250204/miniconda3/envs/jyq_ray/lib/libtinfo.so.6: no version information available (required by bash)
2026-03-31 10:52:14  Collecting environment information...
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14          System Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  OS                           : Ubuntu 22.04.5 LTS (x86_64)
2026-03-31 10:52:14  GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
2026-03-31 10:52:14  Clang version                : Could not collect
2026-03-31 10:52:14  CMake version                : version 3.22.1
2026-03-31 10:52:14  Libc version                 : glibc-2.35
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14         PyTorch Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  PyTorch version              : 2.10.0+cu128
2026-03-31 10:52:14  Is debug build               : False
2026-03-31 10:52:14  CUDA used to build PyTorch   : 12.8
2026-03-31 10:52:14  ROCM used to build PyTorch   : N/A
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14        Python Environment
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Python version               : 3.12.9 | packaged by Anaconda, Inc. | (main, Feb  6 2025, 18:56:27) [GCC 11.2.0] (64-bit runtime)
2026-03-31 10:52:14  Python platform              : Linux-5.15.0-105-generic-x86_64-with-glibc2.35
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14         CUDA / GPU Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Is CUDA available            : True
2026-03-31 10:52:14  CUDA runtime version         : Could not collect
2026-03-31 10:52:14  CUDA_MODULE_LOADING set to   : 
2026-03-31 10:52:14  GPU models and configuration : 
2026-03-31 10:52:14  GPU 0: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 1: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 2: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 3: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 4: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 5: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 6: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 7: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  
2026-03-31 10:52:14  Nvidia driver version        : 535.183.06
2026-03-31 10:52:14  cuDNN version                : Probably one of the following:
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
2026-03-31 10:52:14  HIP runtime version          : N/A
2026-03-31 10:52:14  MIOpen runtime version       : N/A
2026-03-31 10:52:14  Is XNNPACK available         : True
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14            CPU Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Architecture:                       x86_64
2026-03-31 10:52:14  CPU op-mode(s):                     32-bit, 64-bit
2026-03-31 10:52:14  Address sizes:                      46 bits physical, 57 bits virtual
2026-03-31 10:52:14  Byte Order:                         Little Endian
2026-03-31 10:52:14  CPU(s):                             192
2026-03-31 10:52:14  On-line CPU(s) list:                0-41,48-89,96-137,144-185
2026-03-31 10:52:14  Off-line CPU(s) list:               42-47,90-95,138-143,186-191
2026-03-31 10:52:14  Vendor ID:                          GenuineIntel
2026-03-31 10:52:14  Model name:                         INTEL(R) XEON(R) PLATINUM 8558
2026-03-31 10:52:14  CPU family:                         6
2026-03-31 10:52:14  Model:                              207
2026-03-31 10:52:14  Thread(s) per core:                 2
2026-03-31 10:52:14  Core(s) per socket:                 48
2026-03-31 10:52:14  Socket(s):                          2
2026-03-31 10:52:14  Stepping:                           2
2026-03-31 10:52:14  CPU max MHz:                        4000.0000
2026-03-31 10:52:14  CPU min MHz:                        800.0000
2026-03-31 10:52:14  BogoMIPS:                           4200.00
2026-03-31 10:52:14  Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
2026-03-31 10:52:14  Virtualization:                     VT-x
2026-03-31 10:52:14  L1d cache:                          4.5 MiB (96 instances)
2026-03-31 10:52:14  L1i cache:                          3 MiB (96 instances)
2026-03-31 10:52:14  L2 cache:                           192 MiB (96 instances)
2026-03-31 10:52:14  L3 cache:                           520 MiB (2 instances)
2026-03-31 10:52:14  NUMA node(s):                       2
2026-03-31 10:52:14  NUMA node0 CPU(s):                  0-47,96-143
2026-03-31 10:52:14  NUMA node1 CPU(s):                  48-95,144-191
2026-03-31 10:52:14  Vulnerability Gather data sampling: Not affected
2026-03-31 10:52:14  Vulnerability Itlb multihit:        Not affected
2026-03-31 10:52:14  Vulnerability L1tf:                 Not affected
2026-03-31 10:52:14  Vulnerability Mds:                  Not affected
2026-03-31 10:52:14  Vulnerability Meltdown:             Not affected
2026-03-31 10:52:14  Vulnerability Mmio stale data:      Not affected
2026-03-31 10:52:14  Vulnerability Retbleed:             Not affected
2026-03-31 10:52:14  Vulnerability Spec rstack overflow: Not affected
2026-03-31 10:52:14  Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
2026-03-31 10:52:14  Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
2026-03-31 10:52:14  Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
2026-03-31 10:52:14  Vulnerability Srbds:                Not affected
2026-03-31 10:52:14  Vulnerability Tsx async abort:      Not affected
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Versions of relevant libraries
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  [pip3] flash_attn==2.8.3+cu128torch2.10
2026-03-31 10:52:14  [pip3] flashinfer-python==0.6.4
2026-03-31 10:52:14  [pip3] numpy==2.2.6
2026-03-31 10:52:14  [pip3] nvidia-cublas-cu12==12.8.4.1
2026-03-31 10:52:14  [pip3] nvidia-cuda-cupti-cu12==12.8.90
2026-03-31 10:52:14  [pip3] nvidia-cuda-nvrtc-cu12==12.8.93
2026-03-31 10:52:14  [pip3] nvidia-cuda-runtime-cu12==12.8.90
2026-03-31 10:52:14  [pip3] nvidia-cudnn-cu12==9.10.2.21
2026-03-31 10:52:14  [pip3] nvidia-cudnn-frontend==1.18.0
2026-03-31 10:52:14  [pip3] nvidia-cufft-cu12==11.3.3.83
2026-03-31 10:52:14  [pip3] nvidia-cufile-cu12==1.13.1.3
2026-03-31 10:52:14  [pip3] nvidia-curand-cu12==10.3.9.90
2026-03-31 10:52:14  [pip3] nvidia-cusolver-cu12==11.7.3.90
2026-03-31 10:52:14  [pip3] nvidia-cusparse-cu12==12.5.8.93
2026-03-31 10:52:14  [pip3] nvidia-cusparselt-cu12==0.7.1
2026-03-31 10:52:14  [pip3] nvidia-cutlass-dsl==4.4.2
2026-03-31 10:52:14  [pip3] nvidia-cutlass-dsl-libs-base==4.4.2
2026-03-31 10:52:14  [pip3] nvidia-ml-py==13.595.45
2026-03-31 10:52:14  [pip3] nvidia-nccl-cu12==2.27.5
2026-03-31 10:52:14  [pip3] nvidia-nvjitlink-cu12==12.8.93
2026-03-31 10:52:14  [pip3] nvidia-nvshmem-cu12==3.4.5
2026-03-31 10:52:14  [pip3] nvidia-nvtx-cu12==12.8.90
2026-03-31 10:52:14  [pip3] pyzmq==27.1.0
2026-03-31 10:52:14  [pip3] torch==2.10.0+cu128
2026-03-31 10:52:14  [pip3] torch_c_dlpack_ext==0.1.5
2026-03-31 10:52:14  [pip3] torchaudio==2.10.0
2026-03-31 10:52:14  [pip3] torchvision==0.25.0+cu128
2026-03-31 10:52:14  [pip3] transformers==4.57.6
2026-03-31 10:52:14  [pip3] triton==3.6.0
2026-03-31 10:52:14  [conda] numpy                     1.26.4                   pypi_0    pypi
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14           vLLM Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  ROCM Version                 : Could not collect
2026-03-31 10:52:14  vLLM Version                 : 0.17.1
2026-03-31 10:52:14  vLLM Build Flags:
2026-03-31 10:52:14    CUDA Archs: Not Set; ROCm: Disabled
2026-03-31 10:52:14  GPU Topology:
2026-03-31 10:52:14    	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	CPU Affinity	NUMA Affinity	GPU NUMA ID
2026-03-31 10:52:14  GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	PIX	NODE	NODE	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	NODE	PIX	NODE	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	NODE	NODE	PIX	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PIX	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  NIC0	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:14  NIC1	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	NODE	 X 	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:65 -- --------------------------------------------------------
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:66 -- Job 'raysubmit-1774925511-jo-dcq42sipnlhjwfx4' succeeded
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:67 -- --------------------------------------------------------
2026-03-31 10:52:18  NIC2	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	NODE	NODE	 X 	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  NIC3	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  NIC4	SYS	SYS	SYS	SYS	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC5	SYS	SYS	SYS	SYS	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	NODE	 X 	NODE	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC6	SYS	SYS	SYS	SYS	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	NODE	NODE	 X 	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC7	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	NODE	SYS				
2026-03-31 10:52:18  NIC8	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	SYS				
2026-03-31 10:52:18  NIC9	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	 X 				
2026-03-31 10:52:18  
2026-03-31 10:52:18  Legend:
2026-03-31 10:52:18  
2026-03-31 10:52:18    X    = Self
2026-03-31 10:52:18    SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
2026-03-31 10:52:18    NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
2026-03-31 10:52:18    PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
2026-03-31 10:52:18    PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
2026-03-31 10:52:18    PIX  = Connection traversing at most a single PCIe bridge
2026-03-31 10:52:18    NV#  = Connection traversing a bonded set of # NVLinks
2026-03-31 10:52:18  
2026-03-31 10:52:18  NIC Legend:
2026-03-31 10:52:18  
2026-03-31 10:52:18    NIC0: mlx5_100
2026-03-31 10:52:18    NIC1: mlx5_101
2026-03-31 10:52:18    NIC2: mlx5_102
2026-03-31 10:52:18    NIC3: mlx5_103
2026-03-31 10:52:18    NIC4: mlx5_104
2026-03-31 10:52:18    NIC5: mlx5_105
2026-03-31 10:52:18    NIC6: mlx5_106
2026-03-31 10:52:18    NIC7: mlx5_107
2026-03-31 10:52:18    NIC8: mlx5_200
2026-03-31 10:52:18    NIC9: mlx5_bond_0
2026-03-31 10:52:18  
2026-03-31 10:52:18  ==============================
2026-03-31 10:52:18       Environment Variables
2026-03-31 10:52:18  ==============================
2026-03-31 10:52:18  NVIDIA_VISIBLE_DEVICES=GPU-1d8be956-89d8-84ab-cba7-8f7960c1b7ce,GPU-ca7a0045-8c51-2515-ebf1-2a1a37d0be05,GPU-9d16e982-e85f-dec3-f5e3-b4cc13790f06,GPU-dec51dda-cbc2-242c-c825-f8a451b0bda0,GPU-dad83634-95ad-8f59-f3d0-e443c945324f,GPU-064ed4be-801d-7269-c08d-3451360f0df1,GPU-a71b93e8-bcb9-694e-0184-63fb0d4f5bf6,GPU-22416d4b-4e6e-cbeb-f3bc-b1aa66370d32
2026-03-31 10:52:18  NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566
2026-03-31 10:52:18  NCCL_VERSION=2.25.1-1
2026-03-31 10:52:18  NCCL_SOCKET_IFNAME=eth0
2026-03-31 10:52:18  NCCL_DEBUG_SUBSYS=ALL
2026-03-31 10:52:18  NVIDIA_DRIVER_CAPABILITIES=all
2026-03-31 10:52:18  NCCL_DEBUG=INFO
2026-03-31 10:52:18  NVIDIA_PRODUCT_NAME=CUDA
2026-03-31 10:52:18  CUDA_VERSION=12.8.1
2026-03-31 10:52:18  LD_LIBRARY_PATH=/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
2026-03-31 10:52:18  OMP_NUM_THREADS=1
2026-03-31 10:52:18  NCCL_IB_RETRY_CNT=7
2026-03-31 10:52:18  NCCL_CROSS_NIC=0
2026-03-31 10:52:18  PYTORCH_NVML_BASED_CUDA_CHECK=1
2026-03-31 10:52:18  TORCHINDUCTOR_COMPILE_THREADS=1
2026-03-31 10:52:18  TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
2026-03-31 10:52:18  
2026-03-31 10:52:18  + SUBMIT_EXIT_CODE=0
2026-03-31 10:52:18  + set -e
2026-03-31 10:52:18  + '[' 0 -eq 0 ']'
2026-03-31 10:52:18  Job raysubmit-1774925511-jo-dcq42sipnlhjwfx4 completed successfully.
2026-03-31 10:52:18  + echo 'Job raysubmit-1774925511-jo-dcq42sipnlhjwfx4 completed successfully.'
2026-03-31 10:52:18  + exit 0
2026-03-31 10:52:18  + cleanup
2026-03-31 10:52:18  + local status=0
2026-03-31 10:52:18  + trap - EXIT INT TERM
2026-03-31 10:52:18  Stopping Ray cluster...
2026-03-31 10:52:18  + echo 'Stopping Ray cluster...'
2026-03-31 10:52:18  + ray stop --force
2026-03-31 10:51:51  Total Usage:
2026-03-31 10:51:51   0.0/336.0 CPU
2026-03-31 10:51:51   0.0/16.0 GPU
2026-03-31 10:51:51   0B/3.23TiB memory
2026-03-31 10:51:51   0B/372.53GiB object_store_memory
2026-03-31 10:51:51  
2026-03-31 10:51:51  From request_resources:
2026-03-31 10:51:51   (none)
2026-03-31 10:51:51  Pending Demands:
2026-03-31 10:51:51   (no resource demands)
2026-03-31 10:51:51  ==========================================
2026-03-31 10:51:51  + echo ==========================================
2026-03-31 10:51:51  ++ cat
2026-03-31 10:51:51  + USER_COMMAND='#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py'
2026-03-31 10:51:51  ++ cat
2026-03-31 10:51:51  + RUNTIME_ENV='{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}'
2026-03-31 10:51:51  + '[' -n '#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py' ']'
2026-03-31 10:51:51  Ray cluster is ready. Submitting user command as a job...
2026-03-31 10:51:51  + echo 'Ray cluster is ready. Submitting user command as a job...'
2026-03-31 10:51:51  ++ date +%s
2026-03-31 10:51:51  + JOB_ID=raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:51  Submitting job with ID: raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:51  + echo 'Submitting job with ID: raysubmit-1774925511-jo-dcq42sipnlhjwfx4'
2026-03-31 10:51:51  + RAY_ADDRESS=http://127.0.0.1:8265
2026-03-31 10:51:51  + set +e
2026-03-31 10:51:51  + '[' -n '{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}' ']'
2026-03-31 10:51:51  + ray job submit --address http://127.0.0.1:8265 --submission-id raysubmit-1774925511-jo-dcq42sipnlhjwfx4 --runtime-env-json '{"working_dir":"/mnt/c20250204_hs/jyq/deepseek","py_modules":null,"py_executable":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin/python","excludes":[],"pip":null,"uv":null,"conda":null,"env_vars":{"ATLAS_CHECK_ENABLE":"JobInit;JobFailed","ATLAS_REBOOT_ENABLE":"JobFailed","LD_LIBRARY_PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64","NCCL_DEBUG":"INFO","NCCL_DEBUG_SUBSYS":"ALL","NCCL_IB_RETRY_CNT":"7","PATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/bin:/home/ray/anaconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin","PYTHONPATH":"/mnt/c20250204/miniconda3/envs/jyq_ray/lib/python3.12/site-packages","RAY_CGRAPH_get_timeout":"1800"},"nsight":null,"image_uri":"","config":null}' -- bash -lc '#source "/mnt/c20250204/miniconda3/etc/profile.d/conda.sh" && conda activate jyq_ray
2026-03-31 10:51:51  #cd /mnt/c20250204_hs/jyq/deepseek
2026-03-31 10:51:51  python collect_env.py'
2026-03-31 10:51:52  2026-03-31 10:51:52,906	INFO cli.py:41 -- Job submission server address: http://127.0.0.1:8265
2026-03-31 10:51:53  2026-03-31 10:51:53,101	INFO dashboard_sdk.py:338 -- Uploading package gcs://_ray_pkg_af2613c049db5f5c.zip.
2026-03-31 10:51:53  2026-03-31 10:51:53,102	INFO packaging.py:588 -- Creating a file package for local module '/mnt/c20250204_hs/jyq/deepseek'.
2026-03-31 10:51:53  2026-03-31 10:51:53,337	INFO job_manager.py:568 -- Runtime env is setting up.
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:65 -- ---------------------------------------------------------------------
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:66 -- Job 'raysubmit-1774925511-jo-dcq42sipnlhjwfx4' submitted successfully
2026-03-31 10:51:53  2026-03-31 10:51:53,472	SUCC cli.py:67 -- ---------------------------------------------------------------------
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:291 -- Next steps
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:292 -- Query the logs of the job:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:294 -- ray job logs raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:296 -- Query the status of the job:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:298 -- ray job status raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:300 -- Request the job to be stopped:
2026-03-31 10:51:53  2026-03-31 10:51:53,473	INFO cli.py:302 -- ray job stop raysubmit-1774925511-jo-dcq42sipnlhjwfx4
2026-03-31 10:51:53  2026-03-31 10:51:53,474	INFO cli.py:312 -- Tailing logs until the job exits (disable with --no-wait):
2026-03-31 10:52:14  bash: /mnt/c20250204/miniconda3/envs/jyq_ray/lib/libtinfo.so.6: no version information available (required by bash)
2026-03-31 10:52:14  Collecting environment information...
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14          System Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  OS                           : Ubuntu 22.04.5 LTS (x86_64)
2026-03-31 10:52:14  GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
2026-03-31 10:52:14  Clang version                : Could not collect
2026-03-31 10:52:14  CMake version                : version 3.22.1
2026-03-31 10:52:14  Libc version                 : glibc-2.35
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14         PyTorch Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  PyTorch version              : 2.10.0+cu128
2026-03-31 10:52:14  Is debug build               : False
2026-03-31 10:52:14  CUDA used to build PyTorch   : 12.8
2026-03-31 10:52:14  ROCM used to build PyTorch   : N/A
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14        Python Environment
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Python version               : 3.12.9 | packaged by Anaconda, Inc. | (main, Feb  6 2025, 18:56:27) [GCC 11.2.0] (64-bit runtime)
2026-03-31 10:52:14  Python platform              : Linux-5.15.0-105-generic-x86_64-with-glibc2.35
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14         CUDA / GPU Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Is CUDA available            : True
2026-03-31 10:52:14  CUDA runtime version         : Could not collect
2026-03-31 10:52:14  CUDA_MODULE_LOADING set to   : 
2026-03-31 10:52:14  GPU models and configuration : 
2026-03-31 10:52:14  GPU 0: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 1: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 2: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 3: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 4: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 5: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 6: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  GPU 7: NVIDIA H100 80GB HBM3
2026-03-31 10:52:14  
2026-03-31 10:52:14  Nvidia driver version        : 535.183.06
2026-03-31 10:52:14  cuDNN version                : Probably one of the following:
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
2026-03-31 10:52:14  /usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
2026-03-31 10:52:14  HIP runtime version          : N/A
2026-03-31 10:52:14  MIOpen runtime version       : N/A
2026-03-31 10:52:14  Is XNNPACK available         : True
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14            CPU Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Architecture:                       x86_64
2026-03-31 10:52:14  CPU op-mode(s):                     32-bit, 64-bit
2026-03-31 10:52:14  Address sizes:                      46 bits physical, 57 bits virtual
2026-03-31 10:52:14  Byte Order:                         Little Endian
2026-03-31 10:52:14  CPU(s):                             192
2026-03-31 10:52:14  On-line CPU(s) list:                0-41,48-89,96-137,144-185
2026-03-31 10:52:14  Off-line CPU(s) list:               42-47,90-95,138-143,186-191
2026-03-31 10:52:14  Vendor ID:                          GenuineIntel
2026-03-31 10:52:14  Model name:                         INTEL(R) XEON(R) PLATINUM 8558
2026-03-31 10:52:14  CPU family:                         6
2026-03-31 10:52:14  Model:                              207
2026-03-31 10:52:14  Thread(s) per core:                 2
2026-03-31 10:52:14  Core(s) per socket:                 48
2026-03-31 10:52:14  Socket(s):                          2
2026-03-31 10:52:14  Stepping:                           2
2026-03-31 10:52:14  CPU max MHz:                        4000.0000
2026-03-31 10:52:14  CPU min MHz:                        800.0000
2026-03-31 10:52:14  BogoMIPS:                           4200.00
2026-03-31 10:52:14  Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
2026-03-31 10:52:14  Virtualization:                     VT-x
2026-03-31 10:52:14  L1d cache:                          4.5 MiB (96 instances)
2026-03-31 10:52:14  L1i cache:                          3 MiB (96 instances)
2026-03-31 10:52:14  L2 cache:                           192 MiB (96 instances)
2026-03-31 10:52:14  L3 cache:                           520 MiB (2 instances)
2026-03-31 10:52:14  NUMA node(s):                       2
2026-03-31 10:52:14  NUMA node0 CPU(s):                  0-47,96-143
2026-03-31 10:52:14  NUMA node1 CPU(s):                  48-95,144-191
2026-03-31 10:52:14  Vulnerability Gather data sampling: Not affected
2026-03-31 10:52:14  Vulnerability Itlb multihit:        Not affected
2026-03-31 10:52:14  Vulnerability L1tf:                 Not affected
2026-03-31 10:52:14  Vulnerability Mds:                  Not affected
2026-03-31 10:52:14  Vulnerability Meltdown:             Not affected
2026-03-31 10:52:14  Vulnerability Mmio stale data:      Not affected
2026-03-31 10:52:14  Vulnerability Retbleed:             Not affected
2026-03-31 10:52:14  Vulnerability Spec rstack overflow: Not affected
2026-03-31 10:52:14  Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
2026-03-31 10:52:14  Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
2026-03-31 10:52:14  Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
2026-03-31 10:52:14  Vulnerability Srbds:                Not affected
2026-03-31 10:52:14  Vulnerability Tsx async abort:      Not affected
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  Versions of relevant libraries
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  [pip3] flash_attn==2.8.3+cu128torch2.10
2026-03-31 10:52:14  [pip3] flashinfer-python==0.6.4
2026-03-31 10:52:14  [pip3] numpy==2.2.6
2026-03-31 10:52:14  [pip3] nvidia-cublas-cu12==12.8.4.1
2026-03-31 10:52:14  [pip3] nvidia-cuda-cupti-cu12==12.8.90
2026-03-31 10:52:14  [pip3] nvidia-cuda-nvrtc-cu12==12.8.93
2026-03-31 10:52:14  [pip3] nvidia-cuda-runtime-cu12==12.8.90
2026-03-31 10:52:14  [pip3] nvidia-cudnn-cu12==9.10.2.21
2026-03-31 10:52:14  [pip3] nvidia-cudnn-frontend==1.18.0
2026-03-31 10:52:14  [pip3] nvidia-cufft-cu12==11.3.3.83
2026-03-31 10:52:14  [pip3] nvidia-cufile-cu12==1.13.1.3
2026-03-31 10:52:14  [pip3] nvidia-curand-cu12==10.3.9.90
2026-03-31 10:52:14  [pip3] nvidia-cusolver-cu12==11.7.3.90
2026-03-31 10:52:14  [pip3] nvidia-cusparse-cu12==12.5.8.93
2026-03-31 10:52:14  [pip3] nvidia-cusparselt-cu12==0.7.1
2026-03-31 10:52:14  [pip3] nvidia-cutlass-dsl==4.4.2
2026-03-31 10:52:14  [pip3] nvidia-cutlass-dsl-libs-base==4.4.2
2026-03-31 10:52:14  [pip3] nvidia-ml-py==13.595.45
2026-03-31 10:52:14  [pip3] nvidia-nccl-cu12==2.27.5
2026-03-31 10:52:14  [pip3] nvidia-nvjitlink-cu12==12.8.93
2026-03-31 10:52:14  [pip3] nvidia-nvshmem-cu12==3.4.5
2026-03-31 10:52:14  [pip3] nvidia-nvtx-cu12==12.8.90
2026-03-31 10:52:14  [pip3] pyzmq==27.1.0
2026-03-31 10:52:14  [pip3] torch==2.10.0+cu128
2026-03-31 10:52:14  [pip3] torch_c_dlpack_ext==0.1.5
2026-03-31 10:52:14  [pip3] torchaudio==2.10.0
2026-03-31 10:52:14  [pip3] torchvision==0.25.0+cu128
2026-03-31 10:52:14  [pip3] transformers==4.57.6
2026-03-31 10:52:14  [pip3] triton==3.6.0
2026-03-31 10:52:14  [conda] numpy                     1.26.4                   pypi_0    pypi
2026-03-31 10:52:14  
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14           vLLM Info
2026-03-31 10:52:14  ==============================
2026-03-31 10:52:14  ROCM Version                 : Could not collect
2026-03-31 10:52:14  vLLM Version                 : 0.17.1
2026-03-31 10:52:14  vLLM Build Flags:
2026-03-31 10:52:14    CUDA Archs: Not Set; ROCm: Disabled
2026-03-31 10:52:14  GPU Topology:
2026-03-31 10:52:14    	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	CPU Affinity	NUMA Affinity	GPU NUMA ID
2026-03-31 10:52:14  GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	SYS	NODE	0-41,96-137	0		N/A
2026-03-31 10:52:14  GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	PIX	NODE	NODE	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	NODE	PIX	NODE	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	NODE	NODE	PIX	NODE	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PIX	NODE	SYS	48-89,144-185	1		N/A
2026-03-31 10:52:14  NIC0	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:14  NIC1	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	NODE	 X 	NODE	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:65 -- --------------------------------------------------------
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:66 -- Job 'raysubmit-1774925511-jo-dcq42sipnlhjwfx4' succeeded
2026-03-31 10:52:18  2026-03-31 10:52:18,585	SUCC cli.py:67 -- --------------------------------------------------------
2026-03-31 10:52:18  NIC2	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	NODE	NODE	 X 	NODE	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  NIC3	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	SYS	SYS	SYS	SYS	SYS	NODE				
2026-03-31 10:52:18  NIC4	SYS	SYS	SYS	SYS	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC5	SYS	SYS	SYS	SYS	NODE	PIX	NODE	NODE	SYS	SYS	SYS	SYS	NODE	 X 	NODE	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC6	SYS	SYS	SYS	SYS	NODE	NODE	PIX	NODE	SYS	SYS	SYS	SYS	NODE	NODE	 X 	NODE	NODE	SYS				
2026-03-31 10:52:18  NIC7	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PIX	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	NODE	SYS				
2026-03-31 10:52:18  NIC8	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	SYS				
2026-03-31 10:52:18  NIC9	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	 X 				
2026-03-31 10:52:18  
2026-03-31 10:52:18  Legend:
2026-03-31 10:52:18  
2026-03-31 10:52:18    X    = Self
2026-03-31 10:52:18    SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
2026-03-31 10:52:18    NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
2026-03-31 10:52:18    PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
2026-03-31 10:52:18    PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
2026-03-31 10:52:18    PIX  = Connection traversing at most a single PCIe bridge
2026-03-31 10:52:18    NV#  = Connection traversing a bonded set of # NVLinks
2026-03-31 10:52:18  
2026-03-31 10:52:18  NIC Legend:
2026-03-31 10:52:18  
2026-03-31 10:52:18    NIC0: mlx5_100
2026-03-31 10:52:18    NIC1: mlx5_101
2026-03-31 10:52:18    NIC2: mlx5_102
2026-03-31 10:52:18    NIC3: mlx5_103
2026-03-31 10:52:18    NIC4: mlx5_104
2026-03-31 10:52:18    NIC5: mlx5_105
2026-03-31 10:52:18    NIC6: mlx5_106
2026-03-31 10:52:18    NIC7: mlx5_107
2026-03-31 10:52:18    NIC8: mlx5_200
2026-03-31 10:52:18    NIC9: mlx5_bond_0
2026-03-31 10:52:18  
2026-03-31 10:52:18  ==============================
2026-03-31 10:52:18       Environment Variables
2026-03-31 10:52:18  ==============================
2026-03-31 10:52:18  NVIDIA_VISIBLE_DEVICES=GPU-1d8be956-89d8-84ab-cba7-8f7960c1b7ce,GPU-ca7a0045-8c51-2515-ebf1-2a1a37d0be05,GPU-9d16e982-e85f-dec3-f5e3-b4cc13790f06,GPU-dec51dda-cbc2-242c-c825-f8a451b0bda0,GPU-dad83634-95ad-8f59-f3d0-e443c945324f,GPU-064ed4be-801d-7269-c08d-3451360f0df1,GPU-a71b93e8-bcb9-694e-0184-63fb0d4f5bf6,GPU-22416d4b-4e6e-cbeb-f3bc-b1aa66370d32
2026-03-31 10:52:18  NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566
2026-03-31 10:52:18  NCCL_VERSION=2.25.1-1
2026-03-31 10:52:18  NCCL_SOCKET_IFNAME=eth0
2026-03-31 10:52:18  NCCL_DEBUG_SUBSYS=ALL
2026-03-31 10:52:18  NVIDIA_DRIVER_CAPABILITIES=all
2026-03-31 10:52:18  NCCL_DEBUG=INFO
2026-03-31 10:52:18  NVIDIA_PRODUCT_NAME=CUDA
2026-03-31 10:52:18  CUDA_VERSION=12.8.1
2026-03-31 10:52:18  LD_LIBRARY_PATH=/mnt/c20250204/miniconda3/envs/jyq_ray/lib:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
2026-03-31 10:52:18  OMP_NUM_THREADS=1
2026-03-31 10:52:18  NCCL_IB_RETRY_CNT=7
2026-03-31 10:52:18  NCCL_CROSS_NIC=0
2026-03-31 10:52:18  PYTORCH_NVML_BASED_CUDA_CHECK=1
2026-03-31 10:52:18  TORCHINDUCTOR_COMPILE_THREADS=1
2026-03-31 10:52:18  TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
2026-03-31 10:52:18  
2026-03-31 10:52:18  + SUBMIT_EXIT_CODE=0
2026-03-31 10:52:18  + set -e
2026-03-31 10:52:18  + '[' 0 -eq 0 ']'
2026-03-31 10:52:18  Job raysubmit-1774925511-jo-dcq42sipnlhjwfx4 completed successfully.
2026-03-31 10:52:18  + echo 'Job raysubmit-1774925511-jo-dcq42sipnlhjwfx4 completed successfully.'
2026-03-31 10:52:18  + exit 0
2026-03-31 10:52:18  + cleanup
2026-03-31 10:52:18  + local status=0
2026-03-31 10:52:18  + trap - EXIT INT TERM
2026-03-31 10:52:18  Stopping Ray cluster...
2026-03-31 10:52:18  + echo 'Stopping Ray cluster...'
2026-03-31 10:52:18  + ray stop --force