[Bug]: vllm is crashed suddenly and stopped #2134
Description
Your current environment
The output of python collect_env.py
Calling add_step_closure function does not have any effect. It's lazy mode only functionality. (warning logged once)
Calling mark_step function does not have any effect. It's lazy mode only functionality. (warning logged once)
Calling iter_mark_step function does not have any effect. It's lazy mode only functionality. (warning logged once)
INFO 11-12 12:17:24 [__init__.py:254] Automatically detected platform hpu.
Collecting environment information...
/usr/local/lib/python3.10/dist-packages/_distutils_hack/__init__.py:30: UserWarning: Setuptools is replacing distutils. Support for replacing an already imported distutils is deprecated. In the future, this condition will fail. Register concerns at https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml
warnings.warn(
==============================
System Info
==============================
OS : Ubuntu 22.04.5 LTS (x86_64)
GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version : Could not collect
CMake version : version 3.22.1
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.6.0+hpu_1.21.3-57.gitabf798b
Is debug build : False
CUDA used to build PyTorch : None
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-6.8.0-85-generic-x86_64-with-glibc2.35
==============================
CUDA / GPU Info
==============================
Is CUDA available : False
CUDA runtime version : No CUDA
CUDA_MODULE_LOADING set to : N/A
GPU models and configuration : No CUDA
Nvidia driver version : No CUDA
cuDNN version : No CUDA
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
==============================
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 192
On-line CPU(s) list: 0-191
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8457C
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
Stepping: 8
CPU max MHz: 3800.0000
CPU min MHz: 800.0000
BogoMIPS: 5200.00
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 monitor 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 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi 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 ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 4.5 MiB (96 instances)
L1i cache: 3 MiB (96 instances)
L2 cache: 192 MiB (96 instances)
L3 cache: 195 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] habana-torch-dataloader==1.21.3.57
[pip3] habana-torch-plugin==1.21.3.57
[pip3] numpy==2.2.6
[pip3] nvidia-ml-py==12.575.51
[pip3] pynvml==12.0.0
[pip3] pytorch-lightning==2.5.2
[pip3] pyzmq==27.1.0
[pip3] torch==2.6.0+hpu.1.21.3.57.gitabf798b
[pip3] torch_tb_profiler==0.4.0
[pip3] torchaudio==2.6.0+cpu
[pip3] torchdata==0.10.1+cpu
[pip3] torchmetrics==1.8.0
[pip3] torchtext==0.18.0+cpu
[pip3] torchvision==0.21.0+cpu
[pip3] transformers==4.57.1
[pip3] triton==3.1.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.9.0.2.dev85+gaudi.1.22.0.gefad474c0 (git sha: audi, date: efad474c0)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
Could not collect
==============================
Environment Variables
==============================
LD_LIBRARY_PATH=/opt/amazon/openmpi/lib:/usr/lib/habanalabs:
TORCHINDUCTOR_COMPILE_THREADS=1
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
🐛 Describe the bug
Vllm exception message:
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
INFO: 10.191.19.64:54016 - "POST /v1/chat/completions HTTP/1.1" 200 OK
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 6) 10:29:11 [No progress error]
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 4) 10:29:11 [No progress error]
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 1) 10:29:11 [No progress error]
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 0) 10:29:11 [No progress error]
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 3) 10:29:12 [No progress error]
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 5) 10:29:12 [No progress error]
Synapse detected a device critical error that requires a restart. Killing process in 5 seconds (hl: 2) 10:29:12 [No progress error]
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
INFO: 10.109.20.86:55372 - "GET /metrics HTTP/1.1" 200 OK
ERROR 11-12 10:29:28 [client.py:309] RuntimeError('Engine process (pid 514) died.')
ERROR 11-12 10:29:28 [client.py:309] NoneType: None
INFO: Shutting down
INFO: Waiting for connections to close. (CTRL+C to force quit)
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
ERROR 11-12 10:29:35 [serving_chat.py:948] Error in chat completion stream generator.
ERROR 11-12 10:29:35 [serving_chat.py:948] Traceback (most recent call last):
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/entrypoints/openai/serving_chat.py", line 517, in chat_completion_stream_generator
ERROR 11-12 10:29:35 [serving_chat.py:948] async for res in result_generator:
ERROR 11-12 10:29:35 [serving_chat.py:948] File "/opt/ai/vllm-fork/vllm/engine/multiprocessing/client.py", line 679, in _process_request
ERROR 11-12 10:29:35 [serving_chat.py:948] raise request_output
ERROR 11-12 10:29:35 [serving_chat.py:948] vllm.engine.multiprocessing.MQEngineDeadError: Engine loop is not running. Inspect the stacktrace to find the original error: RuntimeError('Engine process (pid 514) died.').
INFO: Waiting for application shutdown.
INFO: Application shutdown complete.
INFO: Finished server process [234]
root@sz2:/home/sp# hl-smi
+-----------------------------------------------------------------------------+
| HL-SMI Version: hl-1.22.1-fw-61.4.2.1 |
| Driver Version: 1.22.1-97ec1a4 |
| Nic Driver Version: 1.22.1-97ec1a4 |
|-------------------------------+----------------------+----------------------+
| AIP Name Persistence-M| Bus-Id Disp.A | Volatile Uncor-Events|
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | AIP-Util Compute M. |
|===============================+======================+======================|
| 0 HL-225D N/A | 0000:18:00.0 N/A | 0 |
| N/A 26C P0 95W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 1 HL-225D N/A | 0000:bb:00.0 N/A | 0 |
| N/A 26C P0 78W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 2 HL-225D N/A | 0000:3c:00.0 N/A | 0 |
| N/A 27C P0 73W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 3 HL-225D N/A | 0000:ca:00.0 N/A | 0 |
| N/A 26C P0 89W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 4 HL-225D N/A | 0000:4b:00.0 N/A | 0 |
| N/A 26C P0 100W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 5 HL-225D N/A | 0000:db:00.0 N/A | 0 |
| N/A 25C P0 94W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 6 HL-225D N/A | 0000:5d:00.0 N/A | 0 |
| N/A 25C P0 96W / 450W | 768MiB / 98304MiB | 0% 0% |
|-------------------------------+----------------------+----------------------+
| 7 HL-225D N/A | 0000:9a:00.0 N/A | 0 |
| N/A 26C P0 75W / 450W | 89390MiB / 98304MiB | 0% 90% |
|-------------------------------+----------------------+----------------------+
| Compute Processes: AIP Memory |
| AIP PID Type Process name Usage |
|=============================================================================|
| 0 N/A N/A N/A N/A |
| 1 N/A N/A N/A N/A |
| 2 N/A N/A N/A N/A |
| 3 N/A N/A N/A N/A |
| 4 N/A N/A N/A N/A |
| 5 N/A N/A N/A N/A |
| 6 N/A N/A N/A N/A |
| 7 647160 C python3 88622MiB
+=============================================================================+
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.