[Bug]: DeepSeek-V3.1-Terminus-BF16 run error

### Your current environment

Collecting environment information...
==============================
        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-5.15.0-88-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 A800-SXM4-80GB
GPU 1: NVIDIA A800-SXM4-80GB
GPU 2: NVIDIA A800-SXM4-80GB
GPU 3: NVIDIA A800-SXM4-80GB
GPU 4: NVIDIA A800-SXM4-80GB
GPU 5: NVIDIA A800-SXM4-80GB
GPU 6: NVIDIA A800-SXM4-80GB
GPU 7: NVIDIA A800-SXM4-80GB

Nvidia driver version        : 550.54.14
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):                             128
On-line CPU(s) list:                0-127
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 32
Socket(s):                          2
Stepping:                           6
CPU max MHz:                        3400.0000
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 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 invpcid_single intel_ppin 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 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          3 MiB (64 instances)
L1i cache:                          2 MiB (64 instances)
L2 cache:                           80 MiB (64 instances)
L3 cache:                           96 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-31,64-95
NUMA node1 CPU(s):                  32-63,96-127
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
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    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV8     NV8     NV8     NV8     NV8     NV8     NV8     PXB     SYS     SYS     SYS     SYS     SYS     0-31,64-95      0               N/A
GPU1    NV8      X      NV8     NV8     NV8     NV8     NV8     NV8     PXB     SYS     SYS     SYS     SYS     SYS     0-31,64-95      0               N/A
GPU2    NV8     NV8      X      NV8     NV8     NV8     NV8     NV8     SYS     PXB     SYS     SYS     SYS     SYS     0-31,64-95      0               N/A
GPU3    NV8     NV8     NV8      X      NV8     NV8     NV8     NV8     SYS     PXB     SYS     SYS     SYS     SYS     0-31,64-95      0               N/A
GPU4    NV8     NV8     NV8     NV8      X      NV8     NV8     NV8     SYS     SYS     SYS     SYS     PXB     SYS     32-63,96-127    1               N/A
GPU5    NV8     NV8     NV8     NV8     NV8      X      NV8     NV8     SYS     SYS     SYS     SYS     PXB     SYS     32-63,96-127    1               N/A
GPU6    NV8     NV8     NV8     NV8     NV8     NV8      X      NV8     SYS     SYS     SYS     SYS     SYS     PXB     32-63,96-127    1               N/A
GPU7    NV8     NV8     NV8     NV8     NV8     NV8     NV8      X      SYS     SYS     SYS     SYS     SYS     PXB     32-63,96-127    1               N/A
NIC0    PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS      X      SYS     SYS     SYS     SYS     SYS
NIC1    SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS      X      SYS     SYS     SYS     SYS
NIC2    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PIX     SYS     SYS
NIC3    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PIX      X      SYS     SYS
NIC4    SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS      X      SYS
NIC5    SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS      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
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5

==============================
     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=bond0
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
VLLM_HOST_IP=10.88.0.81
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1


### 🐛 Describe the bug

GLOO_SOCKET_IFNAME=bond0 NCCL_SOCKET_IFNAME=bond0  NCCL_DEBUG=INFO python3 -m vllm.entrypoints.openai.api_server --model /mnt/DeepSeek-V3.1-Terminus-BF16/ \
--served-model-name DeepSeek-R1 --dtype bfloat16 --trust-remote-code  --quantization None   \
--tensor-parallel-size 8 --pipeline-parallel-size 3  --port 8000 --gpu-memory-utilization 0.95  \
--enable-auto-tool-choice --tool-call-parser deepseek_v31 --reasoning-parser deepseek_v3   --enforce-eager True  \
--chat-template /mnt/DeepSeek-V3.1-Terminus-BF16/assets/tool_chat_template_deepseekv31.jinja --distributed-executor-backend ray

Error executing method 'initialize_from_config'. This might cause deadlock in distributed execution.
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344] Traceback (most recent call last):
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 334, in execute_method
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     return run_method(self, method, args, kwargs)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py", line 479, in run_method
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     return func(*args, **kwargs)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/ray/util/tracing/tracing_helper.py", line 461, in _resume_span
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     return method(self, *_args, **_kwargs)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 320, in initialize_from_config
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     self.worker.initialize_from_config(kv_cache_config)  # type: ignore
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 403, in initialize_from_config
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     self.model_runner.initialize_kv_cache(kv_cache_config)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 5241, in initialize_kv_cache
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     self.initialize_attn_backend(kv_cache_config)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4608, in initialize_attn_backend
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4556, in get_attn_backends_for_group
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     layers = get_layers_from_vllm_config(
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]   File "/usr/local/lib/python3.12/dist-packages/vllm/config/vllm.py", line 1352, in get_layers_from_vllm_config
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]     if isinstance(forward_context[layer_name], layer_type)
ERROR 12-03 18:28:56 [core.py:843] EngineCore failed to start.
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843] Traceback (most recent call last):
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 834, in run_engine_core
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 610, in __init__
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     super().__init__(
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 109, in __init__
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     num_gpu_blocks, num_cpu_blocks, kv_cache_config = self._initialize_kv_caches(
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344]                   ~~~~~~~~~~~~~~~^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]                                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=926) ERROR 12-03 18:28:56 [worker_base.py:344] KeyError: 'model.layers.20.self_attn.attn'
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 251, in _initialize_kv_caches
(EngineCore_DP0 pid=752) (RayWorkerWrapper pid=923) INFO 12-03 18:28:55 [gpu_worker.py:359] Available KV cache memory: 26.98 GiB [repeated 2x across cluster]
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     self.model_executor.initialize_from_config(kv_cache_configs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/abstract.py", line 115, in initialize_from_config
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     self.collective_rpc("initialize_from_config", args=(kv_cache_configs,))
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/ray_executor.py", line 493, in collective_rpc
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     return ray.get(ray_worker_outputs, timeout=timeout)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     return fn(*args, **kwargs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     return func(*args, **kwargs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 2972, in get
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     values, debugger_breakpoint = worker.get_objects(
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]                                   ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 1031, in get_objects
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     raise value.as_instanceof_cause()
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843] ray.exceptions.RayTaskError(KeyError): ray::RayWorkerWrapper.execute_method() (pid=926, ip=10.88.0.81, actor_id=e19d75e707380493eaf967be01000000, repr=<vllm.v1.executor.ray_utils.RayWorkerWrapper object at 0x7fd51b0786e0>)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 345, in execute_method
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     raise e
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 334, in execute_method
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     return run_method(self, method, args, kwargs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py", line 479, in run_method
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     return func(*args, **kwargs)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 320, in initialize_from_config
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     self.worker.initialize_from_config(kv_cache_config)  # type: ignore
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 403, in initialize_from_config
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     self.model_runner.initialize_kv_cache(kv_cache_config)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 5241, in initialize_kv_cache
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     self.initialize_attn_backend(kv_cache_config)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4608, in initialize_attn_backend
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4556, in get_attn_backends_for_group
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     layers = get_layers_from_vllm_config(
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]   File "/usr/local/lib/python3.12/dist-packages/vllm/config/vllm.py", line 1352, in get_layers_from_vllm_config
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]     if isinstance(forward_context[layer_name], layer_type)
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843]                   ~~~~~~~~~~~~~~~^^^^^^^^^^^^
(EngineCore_DP0 pid=752) ERROR 12-03 18:28:56 [core.py:843] KeyError: 'model.layers.20.self_attn.attn'
(EngineCore_DP0 pid=752) Process EngineCore_DP0:
(EngineCore_DP0 pid=752) Traceback (most recent call last):
(EngineCore_DP0 pid=752)   File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_DP0 pid=752)     self.run()
(EngineCore_DP0 pid=752)   File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
(EngineCore_DP0 pid=752)     self._target(*self._args, **self._kwargs)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 847, in run_engine_core
(EngineCore_DP0 pid=752)     raise e
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 834, in run_engine_core
(EngineCore_DP0 pid=752)     engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=752)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 610, in __init__
(EngineCore_DP0 pid=752)     super().__init__(
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 109, in __init__
(EngineCore_DP0 pid=752)     num_gpu_blocks, num_cpu_blocks, kv_cache_config = self._initialize_kv_caches(
(EngineCore_DP0 pid=752)                                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 251, in _initialize_kv_caches
(EngineCore_DP0 pid=752)     self.model_executor.initialize_from_config(kv_cache_configs)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/abstract.py", line 115, in initialize_from_config
(EngineCore_DP0 pid=752)     self.collective_rpc("initialize_from_config", args=(kv_cache_configs,))
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/ray_executor.py", line 493, in collective_rpc
(EngineCore_DP0 pid=752)     return ray.get(ray_worker_outputs, timeout=timeout)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
(EngineCore_DP0 pid=752)     return fn(*args, **kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
(EngineCore_DP0 pid=752)     return func(*args, **kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 2972, in get
(EngineCore_DP0 pid=752)     values, debugger_breakpoint = worker.get_objects(
(EngineCore_DP0 pid=752)                                   ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/ray/_private/worker.py", line 1031, in get_objects
(EngineCore_DP0 pid=752)     raise value.as_instanceof_cause()
(EngineCore_DP0 pid=752) ray.exceptions.RayTaskError(KeyError): ray::RayWorkerWrapper.execute_method() (pid=926, ip=10.88.0.81, actor_id=e19d75e707380493eaf967be01000000, repr=<vllm.v1.executor.ray_utils.RayWorkerWrapper object at 0x7fd51b0786e0>)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 345, in execute_method
(EngineCore_DP0 pid=752)     raise e
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 334, in execute_method
(EngineCore_DP0 pid=752)     return run_method(self, method, args, kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py", line 479, in run_method
(EngineCore_DP0 pid=752)     return func(*args, **kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 320, in initialize_from_config
(EngineCore_DP0 pid=752)     self.worker.initialize_from_config(kv_cache_config)  # type: ignore
(EngineCore_DP0 pid=752)     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 403, in initialize_from_config
(EngineCore_DP0 pid=752)     self.model_runner.initialize_kv_cache(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 5241, in initialize_kv_cache
(EngineCore_DP0 pid=752)     self.initialize_attn_backend(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4608, in initialize_attn_backend
(EngineCore_DP0 pid=752)     attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
(EngineCore_DP0 pid=752)                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4556, in get_attn_backends_for_group
(EngineCore_DP0 pid=752)     layers = get_layers_from_vllm_config(
(EngineCore_DP0 pid=752)              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/config/vllm.py", line 1352, in get_layers_from_vllm_config
(EngineCore_DP0 pid=752)     if isinstance(forward_context[layer_name], layer_type)
(EngineCore_DP0 pid=752)                   ~~~~~~~~~~~~~~~^^^^^^^^^^^^
(EngineCore_DP0 pid=752) KeyError: 'model.layers.20.self_attn.attn'
(EngineCore_DP0 pid=752) 2025-12-03 18:28:56,195        ERROR worker.py:433 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::RayWorkerWrapper.execute_method() (pid=241, ip=10.88.0.82, actor_id=b398b7b932cdeed6ec84015101000000, repr=<vllm.v1.executor.ray_utils.RayWorkerWrapper object at 0x7fa6e2a09640>)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 345, in execute_method
(EngineCore_DP0 pid=752)     raise e
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 334, in execute_method
(EngineCore_DP0 pid=752) INFO 12-03 18:28:56 [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=752)     return run_method(self, method, args, kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py", line 479, in run_method
(EngineCore_DP0 pid=752)     return func(*args, **kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 320, in initialize_from_config
(EngineCore_DP0 pid=752)     self.worker.initialize_from_config(kv_cache_config)  # type: ignore
(EngineCore_DP0 pid=752)     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 403, in initialize_from_config
(EngineCore_DP0 pid=752)     self.model_runner.initialize_kv_cache(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 5241, in initialize_kv_cache
(EngineCore_DP0 pid=752)     self.initialize_attn_backend(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4608, in initialize_attn_backend
(EngineCore_DP0 pid=752)     attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
(EngineCore_DP0 pid=752)                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4556, in get_attn_backends_for_group
(EngineCore_DP0 pid=752)     layers = get_layers_from_vllm_config(
(EngineCore_DP0 pid=752)              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/config/vllm.py", line 1352, in get_layers_from_vllm_config
(EngineCore_DP0 pid=752)     if isinstance(forward_context[layer_name], layer_type)
(EngineCore_DP0 pid=752)                   ~~~~~~~~~~~~~~~^^^^^^^^^^^^
(EngineCore_DP0 pid=752) KeyError: 'model.layers.0.self_attn.attn'
(EngineCore_DP0 pid=752) 2025-12-03 18:28:56,208        ERROR worker.py:433 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::RayWorkerWrapper.execute_method() (pid=240, ip=10.88.0.82, actor_id=e66e9c8671a8361641a0696b01000000, repr=<vllm.v1.executor.ray_utils.RayWorkerWrapper object at 0x7f77cf818680>)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 345, in execute_method
(EngineCore_DP0 pid=752)     raise e
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 334, in execute_method
(EngineCore_DP0 pid=752)     return run_method(self, method, args, kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py", line 479, in run_method
(EngineCore_DP0 pid=752)     return func(*args, **kwargs)
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 320, in initialize_from_config
(EngineCore_DP0 pid=752)     self.worker.initialize_from_config(kv_cache_config)  # type: ignore
(EngineCore_DP0 pid=752)     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 403, in initialize_from_config
(EngineCore_DP0 pid=752)     self.model_runner.initialize_kv_cache(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 5241, in initialize_kv_cache
(EngineCore_DP0 pid=752)     self.initialize_attn_backend(kv_cache_config)
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4608, in initialize_attn_backend
(EngineCore_DP0 pid=752)     attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
(EngineCore_DP0 pid=752)                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 4556, in get_attn_backends_for_group
(EngineCore_DP0 pid=752)     layers = get_layers_from_vllm_config(
(EngineCore_DP0 pid=752)              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=752)   File "/usr/local/lib/python3.12/dist-packages/vllm/config/vllm.py", line 1352, in get_layers_from_vllm_config
(EngineCore_DP0 pid=752)     if isinstance(forward_context[layer_name], layer_type)
(EngineCore_DP0 pid=752)                   ~~~~~~~~~~~~~~~^^^^^^^^^^^^
(EngineCore_DP0 pid=752) KeyError: 'model.layers.0.self_attn.attn'

### Before submitting a new issue...

- [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the [documentation page](https://docs.vllm.ai/en/latest/), which can answer lots of frequently asked questions.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

[Bug]: DeepSeek-V3.1-Terminus-BF16 run error #30017

Your current environment

Collecting environment information...

==============================
PyTorch Info

==============================
Python Environment

==============================
CUDA / GPU Info

==============================
CPU Info

==============================
Versions of relevant libraries

==============================
vLLM Info

==============================
Environment Variables

🐛 Describe the bug

Before submitting a new issue...

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Uh oh!

[Bug]: DeepSeek-V3.1-Terminus-BF16 run error #30017

Description

Your current environment

Collecting environment information...

============================== PyTorch Info

============================== Python Environment

============================== CUDA / GPU Info

============================== CPU Info

============================== Versions of relevant libraries

============================== vLLM Info

============================== Environment Variables

🐛 Describe the bug

Before submitting a new issue...

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions

==============================
PyTorch Info

==============================
Python Environment

==============================
CUDA / GPU Info

==============================
CPU Info

==============================
Versions of relevant libraries

==============================
vLLM Info

==============================
Environment Variables