[Bug]: Inference of Qwen3-VL-235B failed

[ving666]

Your current environment

The output of python collect_env.py

==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.9.0+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.12 (main, Oct 10 2025, 08:52:57) [GCC 11.4.0] (64-bit runtime)
Python platform              : Linux-6.8.0-60-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA RTX 5880 Ada Generation
GPU 1: NVIDIA RTX 5880 Ada Generation
GPU 2: NVIDIA RTX 5880 Ada Generation
GPU 3: NVIDIA RTX 5880 Ada Generation

Nvidia driver version        : 575.57.08
cuDNN version                : Could not collect
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:                        46 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               48
On-line CPU(s) list:                  0-47
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Silver 4410Y
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   12
Socket(s):                            2
Stepping:                             8
CPU max MHz:                          3900.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4000.00
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 hfi 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:                            1.1 MiB (24 instances)
L1i cache:                            768 KiB (24 instances)
L2 cache:                             48 MiB (24 instances)
L3 cache:                             60 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-11,24-35
NUMA node1 CPU(s):                    12-23,36-47
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] flashinfer-python==0.5.3
[pip3] numpy==2.2.0
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.16.0
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.3.1
[pip3] nvidia-ml-py==13.580.82
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.3.20
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] torch==2.9.0+cu129
[pip3] torchaudio==2.9.0+cu129
[pip3] torchvision==0.24.0+cu129
[pip3] transformers==4.57.3
[pip3] triton==3.5.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.12.0
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    SYS     SYS     SYS     SYS     0-11,24-35      0               N/A
GPU1    NODE     X      SYS     SYS     SYS     SYS     0-11,24-35      0               N/A
GPU2    SYS     SYS      X      NODE    NODE    NODE    12-23,36-47     1               N/A
GPU3    SYS     SYS     NODE     X      NODE    NODE    12-23,36-47     1               N/A
NIC0    SYS     SYS     NODE    NODE     X      PIX
NIC1    SYS     SYS     NODE    NODE    PIX      X

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: mlx5_0
  NIC1: mlx5_1

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.9 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 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571
NCCL_SOCKET_IFNAME=ibs11f0,ibs11f1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:1024
CUDA_VISIBLE_DEVICES=0,1,2,3
CUDA_VISIBLE_DEVICES=0,1,2,3
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
VLLM_HOST_IP=192.168.101.1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

[W1205 23:01:20.522197868 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())

🐛 Describe the bug

Using v;;m to infer Qwem3-VL-235B, the log shows that the request was successful, but the model failed to generate a response.
This is my startup command：

vllm serve /root/.cache/huggingface/Qwen3-VL-235B-A22B-Instruct/
--tensor-parallel-size 4
--pipeline-parallel-size 3
--max-model-len 10240
--max_num_seqs 20
--gpu_memory_utilization 0.95
--max_num_batched_tokens 2048
--trust-remote-code
--block-size 32
--enable-chunked-prefill
--enable-prefix-caching
--distributed-executor-backend ray
--enforce-eager
--served-model-name Qwen3-VL-235B-A22B-Instruct-QX
| tee /root/.cache/huggingface/test_235b__251205.log
' &

Below is the error log:

12-05 22:34:04 [loggers.py:236] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 0.0%
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [dump_input.py:72] Dumping input data for V1 LLM engine (v0.12.0) with config: model='/root/.cache/huggingface/Qwen3-VL-235B-A22B-Instruct/', speculative_config=None, tokenizer='/root/.cache/huggingface/Qwen3-VL-235B-A22B-Instruct/', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=10240, download_dir=None, load_format=auto, tensor_parallel_size=4, pipeline_parallel_size=3, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01), seed=0, served_model_name=Qwen3-VL-235B-A22B-Instruct-QX, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>}, 'local_cache_dir': None},
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [dump_input.py:79] Dumping scheduler output for model execution: SchedulerOutput(scheduled_new_reqs=[], scheduled_cached_reqs=CachedRequestData(req_ids=['chatcmpl-89e746732c291d2d'], resumed_req_ids=[], new_token_ids=[[9707]], all_token_ids={chatcmpl-89e746732c291d2d: [151644, 872, 198, 14990, 151645, 198, 151644, 77091, 198, 9707]}, new_block_ids=[null], num_computed_tokens=[9], num_output_tokens=[1]), num_scheduled_tokens={chatcmpl-89e746732c291d2d: 1}, total_num_scheduled_tokens=1, scheduled_spec_decode_tokens={}, scheduled_encoder_inputs={}, num_common_prefix_blocks=[1], finished_req_ids=[], free_encoder_mm_hashes=[], preempted_req_ids=[], pending_structured_output_tokens=false, kv_connector_metadata=null, ec_connector_metadata=null)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [dump_input.py:81] Dumping scheduler stats: SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0003549875754348397, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), connector_prefix_cache_stats=None, kv_cache_eviction_events=[], spec_decoding_stats=None, kv_connector_stats=None, waiting_lora_adapters={}, running_lora_adapters={})
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] EngineCore encountered a fatal error.
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] Traceback (most recent call last):
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/dag/compiled_dag_node.py", line 2525, in _execute_until
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] result = self._dag_output_fetcher.read(timeout)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 312, in read
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] outputs = self._read_list(timeout)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 403, in _read_list
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] raise e
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 385, in _read_list
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] result = c.read(min(remaining_timeout, iteration_timeout))
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/shared_memory_channel.py", line 776, in read
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] return self._channel_dict[self._resolve_actor_id()].read(timeout)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/shared_memory_channel.py", line 480, in read
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ret = self._worker.get_objects(
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 1001, in get_objects
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ] = self.core_worker.get_objects(
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "python/ray/_raylet.pyx", line 2873, in ray._raylet.CoreWorker.get_objects
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "python/ray/includes/common.pxi", line 123, in ray._raylet.check_status
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ray.exceptions.RayChannelTimeoutError: System error: Timed out waiting for object available to read. ObjectID: 007e768e7da845eb498bddc26311bb55310405340100000002e1f505
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845]
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] The above exception was the direct cause of the following exception:
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845]
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] Traceback (most recent call last):
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 836, in run_engine_core
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] engine_core.run_busy_loop()
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 863, in run_busy_loop
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] self._process_engine_step()
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 892, in _process_engine_step
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] outputs, model_executed = self.step_fn()
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 441, in step_with_batch_queue
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] model_output = future.result()
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/ray_utils.py", line 150, in result
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] outputs = ray.get(self.ref_or_refs, timeout=timeout)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] return fn(*args, **kwargs)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] return func(*args, **kwargs)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 2945, in get
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] return object_refs.get(timeout=timeout)
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/experimental/compiled_dag_ref.py", line 115, in get
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] self._dag._execute_until(
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] File "/usr/local/lib/python3.12/dist-packages/ray/dag/compiled_dag_node.py", line 2535, in _execute_until
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] raise RayChannelTimeoutError(
(EngineCore_DP0 pid=579) ERROR 12-05 22:43:45 [core.py:845] ray.exceptions.RayChannelTimeoutError: System error: If the execution is expected to take a long time, increase RAY_CGRAPH_get_timeout which is currently 600 seconds. Otherwise, this may indicate that the execution is hanging.
(EngineCore_DP0 pid=579) INFO 12-05 22:43:45 [ray_executor.py:121] Shutting down Ray distributed executor. If you see error log from logging.cc regarding SIGTERM received, please ignore because this is the expected termination process in Ray.
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2167 -- Tearing down compiled DAG
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, ebea74494add595681fa8eb901000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, a08ade3040230e9440e8389d01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, f3b8be490d685a5a72a186ad01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 8207c5c28dd1bbec13f979eb01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 3ca183b46a32cd32c1d0cc8101000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 547d703b3b2c832906844d3301000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, a78ea2bbcc62bff8fd3b026e01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 9e4ee0292c71cbb3818ba1d701000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,339 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, b11de28c8cf83ee57386a2dc01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,340 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, f2ce2ed881ae26c225f7e89d01000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,340 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 09cee016abcbb572a5c0e78801000000)
(EngineCore_DP0 pid=579) 2025-12-05 22:43:45,340 INFO compiled_dag_node.py:2172 -- Cancelling compiled worker on actor: Actor(RayWorkerWrapper, 6ba6dd69827d314c949f927001000000)
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] AsyncLLM output_handler failed.
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] Traceback (most recent call last):
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 498, in output_handler
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] outputs = await engine_core.get_output_async()
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 885, in get_output_async
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] raise self._format_exception(outputs) from None
(APIServer pid=378) ERROR 12-05 22:43:45 [async_llm.py:546] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] Error in chat completion stream generator.
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] Traceback (most recent call last):
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 498, in output_handler
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] outputs = await engine_core.get_output_async()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 885, in get_output_async
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise self._format_exception(outputs) from None
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] Error in chat completion stream generator.
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] Traceback (most recent call last):
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 498, in output_handler
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] outputs = await engine_core.get_output_async()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 885, in get_output_async
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise self._format_exception(outputs) from None
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
....
.....
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 619, in chat_completion_stream_generator
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] async for res in result_generator:
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 444, in generate
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] out = q.get_nowait() or await q.get()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 70, in get
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise output
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 498, in output_handler
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] outputs = await engine_core.get_output_async()
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 885, in get_output_async
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] raise self.format_exception(outputs) from None
(APIServer pid=378) ERROR 12-05 22:43:45 [serving_chat.py:1287] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) [2025-12-05 22:44:44,904 C 36 36] (raylet) experimental_mutable_object_provider.cc:154: An unexpected system state has occurred. You have likely discovered a bug in Ray. Please report this issue at https://github.com/ray-project/ray/issues and we'll work with you to fix it. Check failed: object_manager->WriteAcquire(info.local_object_id, total_data_size, nullptr, total_metadata_size, info.num_readers, object_backing_store) Status not OK: ChannelError: Channel closed.
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) *** StackTrace Information ***
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf4569a) [0x61fd065f069a] ray::operator<<()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf47cb9) [0x61fd065f2cb9] ray::RayLog::~RayLog()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x3ecf0a) [0x61fd05a97f0a] ray::core::experimental::MutableObjectProvider::HandlePushMutableObject()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x2a9e1f) [0x61fd05954e1f] ray::raylet::NodeManager::HandlePushMutableObject()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x31eb96) [0x61fd059c9b96] ray::rpc::ServerCallImpl<>::HandleRequestImpl()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x844438) [0x61fd05eef438] EventTracker::RecordExecution()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83c147) [0x61fd05ee7147] std::_Function_handler<>::_M_invoke()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83d0eb) [0x61fd05ee80eb] boost::asio::detail::executor_op<>::do_complete()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf10aeb) [0x61fd065bbaeb] boost::asio::detail::scheduler::do_run_one()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf13099) [0x61fd065be099] boost::asio::detail::scheduler::run()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf135a2) [0x61fd065be5a2] boost::asio::io_context::run()
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x22031f) [0x61fd058cb31f] main
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7a87161abd90]
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7a87161abe40] __libc_start_main
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x243007) [0x61fd058ee007]
(EngineCore_DP0 pid=579) (raylet, ip=192.168.101.7)
(EngineCore_DP0 pid=579) (RayWorkerWrapper pid=723) [2025-12-05 22:43:45,428 E 723 992] raylet_client.cc:202: Error pushing mutable object: RpcError: RPC error: Socket closed rpc_code: 14
(EngineCore_DP0 pid=579) (RayWorkerWrapper pid=723) [2025-12-05 22:43:45,428 E 723 992] raylet_client.cc:202: Error pushing mutable object: RpcError: RPC error: Socket closed rpc_code: 14
node
node
(EngineCore_DP0 pid=579) 2025-12-05 22:43:47,909 INFO compiled_dag_node.py:2197 -- Teardown complete
(EngineCore_DP0 pid=579) Process EngineCore_DP0:
(EngineCore_DP0 pid=579) Traceback (most recent call last):
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/dag/compiled_dag_node.py", line 2525, in _execute_until
(EngineCore_DP0 pid=579) result = self._dag_output_fetcher.read(timeout)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 312, in read
(EngineCore_DP0 pid=579) outputs = self._read_list(timeout)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 403, in _read_list
(EngineCore_DP0 pid=579) raise e
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/common.py", line 385, in _read_list
(EngineCore_DP0 pid=579) result = c.read(min(remaining_timeout, iteration_timeout))
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/shared_memory_channel.py", line 776, in read
(EngineCore_DP0 pid=579) return self._channel_dict[self._resolve_actor_id()].read(timeout)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/channel/shared_memory_channel.py", line 480, in read
(EngineCore_DP0 pid=579) ret = self._worker.get_objects(
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 1001, in get_objects
(EngineCore_DP0 pid=579) ] = self.core_worker.get_objects(
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "python/ray/_raylet.pyx", line 2873, in ray._raylet.CoreWorker.get_objects
(EngineCore_DP0 pid=579) File "python/ray/includes/common.pxi", line 123, in ray._raylet.check_status
(EngineCore_DP0 pid=579) ray.exceptions.RayChannelTimeoutError: System error: Timed out waiting for object available to read. ObjectID: 007e768e7da845eb498bddc26311bb55310405340100000002e1f505
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579) The above exception was the direct cause of the following exception:
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579) Traceback (most recent call last):
(EngineCore_DP0 pid=579) File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_DP0 pid=579) self.run()
(EngineCore_DP0 pid=579) File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
(EngineCore_DP0 pid=579) self._target(*self._args, **self._kwargs)
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 847, in run_engine_core
(EngineCore_DP0 pid=579) raise e
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 836, in run_engine_core
(EngineCore_DP0 pid=579) engine_core.run_busy_loop()
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 863, in run_busy_loop
(EngineCore_DP0 pid=579) self._process_engine_step()
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 892, in _process_engine_step
(EngineCore_DP0 pid=579) outputs, model_executed = self.step_fn()
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 441, in step_with_batch_queue
(EngineCore_DP0 pid=579) model_output = future.result()
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/ray_utils.py", line 150, in result
(EngineCore_DP0 pid=579) outputs = ray.get(self.ref_or_refs, timeout=timeout)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
(EngineCore_DP0 pid=579) return fn(*args, **kwargs)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
(EngineCore_DP0 pid=579) return func(*args, **kwargs)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 2945, in get
(EngineCore_DP0 pid=579) return object_refs.get(timeout=timeout)
(EngineCore_DP0 pid=579) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/experimental/compiled_dag_ref.py", line 115, in get
(EngineCore_DP0 pid=579) self._dag._execute_until(
(EngineCore_DP0 pid=579) File "/usr/local/lib/python3.12/dist-packages/ray/dag/compiled_dag_node.py", line 2535, in execute_until
(EngineCore_DP0 pid=579) raise RayChannelTimeoutError(
(EngineCore_DP0 pid=579) ray.exceptions.RayChannelTimeoutError: System error: If the execution is expected to take a long time, increase RAY_CGRAPH_get_timeout which is currently 600 seconds. Otherwise, this may indicate that the execution is hanging.
(EngineCore_DP0 pid=579) (raylet) Raylet is terminated. Termination is unexpected. Possible reasons include: (1) SIGKILL by the user or system OOM killer, (2) Invalid memory access from Raylet causing SIGSEGV or SIGBUS, (3) Other termination signals. Last 20 lines of the Raylet logs:
(EngineCore_DP0 pid=579) - bytes errored: 0
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579) [2025-12-05 22:44:44,904 C 36 36] (raylet) experimental_mutable_object_provider.cc:154: An unexpected system state has occurred. You have likely discovered a bug in Ray. Please report this issue at https://github.com/ray-project/ray/issues and we'll work with you to fix it. Check failed: object_manager->WriteAcquire(info.local_object_id, total_data_size, nullptr, total_metadata_size, info.num_readers, object_backing_store) Status not OK: ChannelError: Channel closed.
(EngineCore_DP0 pid=579) *** StackTrace Information ***
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf4569a) [0x61fd065f069a] ray::operator<<()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf47cb9) [0x61fd065f2cb9] ray::RayLog::~RayLog()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x3ecf0a) [0x61fd05a97f0a] ray::core::experimental::MutableObjectProvider::HandlePushMutableObject()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x2a9e1f) [0x61fd05954e1f] ray::raylet::NodeManager::HandlePushMutableObject()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x31eb96) [0x61fd059c9b96] ray::rpc::ServerCallImpl<>::HandleRequestImpl()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x844438) [0x61fd05eef438] EventTracker::RecordExecution()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83c147) [0x61fd05ee7147] std::_Function_handler<>::_M_invoke()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83d0eb) [0x61fd05ee80eb] boost::asio::detail::executor_op<>::do_complete()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf10aeb) [0x61fd065bbaeb] boost::asio::detail::scheduler::do_run_one()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf13099) [0x61fd065be099] boost::asio::detail::scheduler::run()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf135a2) [0x61fd065be5a2] boost::asio::io_context::run()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x22031f) [0x61fd058cb31f] main
(EngineCore_DP0 pid=579) /usr/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7a87161abd90]
(EngineCore_DP0 pid=579) /usr/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7a87161abe40] _libc_start_main
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x243007) [0x61fd058ee007]
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579) (RayWorkerWrapper pid=219, ip=192.168.101.9) WARNING 12-05 22:32:34 [fused_moe.py:888] Using default MoE config. Performance might be sub-optimal! Config file not found at ['/usr/local/lib/python3.12/dist-packages/vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_RTX_5880_Ada_Generation.json'] [repeated 11x across cluster]
(EngineCore_DP0 pid=579) (RayWorkerWrapper pid=217, ip=192.168.101.9) INFO 12-05 22:32:36 [gpu_worker.py:359] Available KV cache memory: 2.52 GiB [repeated 2x across cluster]
(EngineCore_DP0 pid=579) (RayWorkerWrapper pid=718) [2025-12-05 22:43:45,428 E 718 1039] raylet_client.cc:202: Error pushing mutable object: RpcError: RPC error: Socket closed rpc_code: 14 [repeated 6x across cluster]
(EngineCore_DP0 pid=579) (raylet) Raylet is terminated. Termination is unexpected. Possible reasons include: (1) SIGKILL by the user or system OOM killer, (2) Invalid memory access from Raylet causing SIGSEGV or SIGBUS, (3) Other termination signals. Last 20 lines of the Raylet logs:
(EngineCore_DP0 pid=579) - bytes errored: 0
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579) [2025-12-05 22:44:44,904 C 36 36] (raylet) experimental_mutable_object_provider.cc:154: An unexpected system state has occurred. You have likely discovered a bug in Ray. Please report this issue at https://github.com/ray-project/ray/issues and we'll work with you to fix it. Check failed: object_manager->WriteAcquire(info.local_object_id, total_data_size, nullptr, total_metadata_size, info.num_readers, object_backing_store) Status not OK: ChannelError: Channel closed.
(EngineCore_DP0 pid=579) *** StackTrace Information ***
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf4569a) [0x61fd065f069a] ray::operator<<()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf47cb9) [0x61fd065f2cb9] ray::RayLog::~RayLog()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x3ecf0a) [0x61fd05a97f0a] ray::core::experimental::MutableObjectProvider::HandlePushMutableObject()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x2a9e1f) [0x61fd05954e1f] ray::raylet::NodeManager::HandlePushMutableObject()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x31eb96) [0x61fd059c9b96] ray::rpc::ServerCallImpl<>::HandleRequestImpl()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x844438) [0x61fd05eef438] EventTracker::RecordExecution()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83c147) [0x61fd05ee7147] std::_Function_handler<>::_M_invoke()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x83d0eb) [0x61fd05ee80eb] boost::asio::detail::executor_op<>::do_complete()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf10aeb) [0x61fd065bbaeb] boost::asio::detail::scheduler::do_run_one()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf13099) [0x61fd065be099] boost::asio::detail::scheduler::run()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0xf135a2) [0x61fd065be5a2] boost::asio::io_context::run()
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x22031f) [0x61fd058cb31f] main
(EngineCore_DP0 pid=579) /usr/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7a87161abd90]
(EngineCore_DP0 pid=579) /usr/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7a87161abe40] __libc_start_main
(EngineCore_DP0 pid=579) /usr/local/lib/python3.12/dist-packages/ray/core/src/ray/raylet/raylet(+0x243007) [0x61fd058ee007]
(EngineCore_DP0 pid=579)
(EngineCore_DP0 pid=579)
(APIServer pid=378) INFO: Shutting down
(APIServer pid=378) INFO: Waiting for application shutdown.
(APIServer pid=378) INFO: Application shutdown complete.
(APIServer pid=378) INFO: Finished server process [378]

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.

[ywang96]

This seems a ray issue rather than vLLM (as indicated by the error and --distributed-executor-backend ray)

Is there a particular reason why you need to use ray as the backend instead of MP?

[ving666]

这似乎是rayvLLM 的问题而不是 vLLM 的问题（如错误信息所示--distributed-executor-backend ray）。

您为什么一定要使用 Ray 作为后端而不是 MP 呢？有什么特殊原因吗？

Thank you for your reply. I use three servers for distributed inference, so I use ray+vllm for deployment.