[Bug][WideEP]: API server hangs during DP=16 + DBO on B200 at high concurrency #25491
Description
Your current environment
The output of python collect_env.py
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 : 14.0.0-1ubuntu1.1
CMake version : version 4.1.0
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.8.0+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.11 (main, Jun 4 2025, 08:56:18) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-6.6.97+-x86_64-with-glibc2.35
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.8.93
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration :
GPU 0: NVIDIA B200
GPU 1: NVIDIA B200
GPU 2: NVIDIA B200
GPU 3: NVIDIA B200
GPU 4: NVIDIA B200
GPU 5: NVIDIA B200
GPU 6: NVIDIA B200
GPU 7: NVIDIA B200
Nvidia driver version : 580.65.06
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: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 224
On-line CPU(s) list: 0-223
Vendor ID: GenuineIntel
Model name: INTEL(R) XEON(R) PLATINUM 8581C CPU @ 2.10GHz
CPU family: 6
Model: 207
Thread(s) per core: 2
Core(s) per socket: 56
Socket(s): 2
Stepping: 2
BogoMIPS: 4200.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 5.3 MiB (112 instances)
L1i cache: 3.5 MiB (112 instances)
L2 cache: 224 MiB (112 instances)
L3 cache: 520 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-55,112-167
NUMA node1 CPU(s): 56-111,168-223
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks
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; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.3.1
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.14.1
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-ml-py==13.580.82
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pynvml==13.0.1
[pip3] pyzmq==27.1.0
[pip3] torch==2.8.0+cu128
[pip3] torchaudio==2.8.0+cu128
[pip3] torchvision==0.23.0+cu128
[pip3] transformers==4.56.1
[pip3] triton==3.4.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.1.dev1+g3b56a1848 (git sha: 3b56a1848)
vLLM Build Flags:
CUDA Archs: 9.0a 10.0; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX PIX NODE NODE SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 PIX PIX NODE NODE SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE PIX PIX SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE PIX PIX SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX PIX NODE NODE 56-111,168-223 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS PIX PIX NODE NODE 56-111,168-223 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE PIX PIX 56-111,168-223 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE PIX PIX 56-111,168-223 1 N/A
NIC0 PIX PIX NODE NODE SYS SYS SYS SYS X PIX NODE NODE SYS SYS SYS SYS
NIC1 PIX PIX NODE NODE SYS SYS SYS SYS PIX X NODE NODE SYS SYS SYS SYS
NIC2 NODE NODE PIX PIX SYS SYS SYS SYS NODE NODE X PIX SYS SYS SYS SYS
NIC3 NODE NODE PIX PIX SYS SYS SYS SYS NODE NODE PIX X SYS SYS SYS SYS
NIC4 SYS SYS SYS SYS PIX PIX NODE NODE SYS SYS SYS SYS X PIX NODE NODE
NIC5 SYS SYS SYS SYS PIX PIX NODE NODE SYS SYS SYS SYS PIX X NODE NODE
NIC6 SYS SYS SYS SYS NODE NODE PIX PIX SYS SYS SYS SYS NODE NODE X PIX
NIC7 SYS SYS SYS SYS NODE NODE PIX PIX SYS SYS 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
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
==============================
Environment Variables
==============================
CUDA_HOME=/usr/local/cuda/
CUDA_HOME=/usr/local/cuda/
CUDA_MAJOR=12
CUDA_VERSION=12.8.1
LD_LIBRARY_PATH=/usr/local/nvshmem/lib:/usr/local/nixl/lib/x86_64-linux-gnu:/opt/ucx/lib:/usr/local/lib:/usr/local/gib/lib64:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:
NCCL_CROSS_NIC=0
NCCL_DEBUG=INFO
NCCL_IB_ADAPTIVE_ROUTING=1
NCCL_IB_FIFO_TC=84
NCCL_IB_QPS_PER_CONNECTION=4
NCCL_IB_TC=52
NCCL_NET=gIB
NCCL_NET_GDR_LEVEL=PIX
NCCL_NVLS_CHUNKSIZE=524288
NCCL_P2P_NET_CHUNKSIZE=131072
NCCL_TUNER_CONFIG_PATH=/usr/local/gib/configs/tuner_config_a4.txtpb
NCCL_VERSION=2.25.1-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_GDRCOPY=disabled
NVIDIA_PRODUCT_NAME=CUDA
NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566
NVIDIA_VISIBLE_DEVICES=all
TORCH_CUDA_ARCH_LIST=9.0a 10.0
VLLM_ALL2ALL_BACKEND=deepep_low_latency
VLLM_ATTENTION_BACKEND=CUTLASS_MLA
VLLM_CACHE_ROOT=/root/.nv/ComputeCache/.vllm
VLLM_LOGGING_LEVEL=DEBUG
VLLM_MOE_DP_CHUNK_SIZE=400
VLLM_NIXL_SIDE_CHANNEL_HOST=10.4.2.26
VLLM_NIXL_SIDE_CHANNEL_PORT=6555
VLLM_RANDOMIZE_DP_DUMMY_INPUTS=1
VLLM_TORCH_PROFILER_DIR=/code/traces
VLLM_USE_DEEP_GEMM=1
VLLM_USE_PRECOMPILED=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
When running a 2p2d B200 node configuration with Deepseek v3.1 in DP=16 + DBO for decode, the decode node is encountering a hang at high concurrency (saw this at 2k and at 4k) where requests stop completing.
15 of 16 decode DP ranks are on line:
File "/app/venv/lib/python3.12/site-packages/torch/cuda/streams.py", line 231, in synchronize
super().synchronize()
File "/app/vllm/vllm/v1/worker/gpu_model_runner.py", line 4046, in _to_list
self.transfer_event.synchronize()
and 1 of 16 ranks (rank 7) are at:
<built-in method linear of module object at remote 0x7b3806783100>
File "/app/vllm/vllm/model_executor/layers/utils.py", line 92, in default_unquantized_gemm
return torch.nn.functional.linear(x, weight, bias)
File "/app/vllm/vllm/model_executor/layers/vocab_parallel_embedding.py", line 53, in apply
return dispatch_unquantized_gemm()(layer, x, layer.weight, bias)
File "/app/vllm/vllm/model_executor/layers/logits_processor.py", line 90, in _get_logits
logits = lm_head.quant_method.apply(lm_head,
File "/app/vllm/vllm/model_executor/layers/logits_processor.py", line 58, in forward
logits = self._get_logits(hidden_states, lm_head, embedding_bias)
Configuration for decode ranks 0-7
Prefill server appears to have no issue (DBO is not enabled).
Benchmark is 1:100 in:out
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.