[Bug]: vLLM crashes on B200 when attempting to load Qwen3 due to AttributeError: module 'vllm.envs' has no attribute 'VLLM_USE_TRTLLM_ATTENTION' #22372
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) 11.4.0
Clang version : 14.0.0-1ubuntu1.1
CMake version : version 4.0.3
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.7.1+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-6.6.93+-x86_64-with-glibc2.35
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.9.86
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 : 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: 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 disabled; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.3.14
[pip3] nvidia-cuda-cupti-cu12==12.8.57
[pip3] nvidia-cuda-nvrtc-cu12==12.8.61
[pip3] nvidia-cuda-runtime-cu12==12.8.57
[pip3] nvidia-cudnn-cu12==9.7.1.26
[pip3] nvidia-cudnn-frontend==1.13.0
[pip3] nvidia-cufft-cu12==11.3.3.41
[pip3] nvidia-cufile-cu12==1.13.0.11
[pip3] nvidia-curand-cu12==10.3.9.55
[pip3] nvidia-cusolver-cu12==11.7.2.55
[pip3] nvidia-cusparse-cu12==12.5.7.53
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-ml-py==12.575.51
[pip3] nvidia-nccl-cu12==2.26.2.post1
[pip3] nvidia-nvjitlink-cu12==12.8.61
[pip3] nvidia-nvshmem-cu12==3.3.20
[pip3] nvidia-nvtx-cu12==12.8.55
[pip3] pynvml==12.0.0
[pip3] pyzmq==27.0.1
[pip3] torch==2.7.1+cu128
[pip3] torchaudio==2.7.1+cu128
[pip3] torchvision==0.22.1+cu128
[pip3] transformers==4.55.0
[pip3] triton==3.3.1
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
Neuron SDK Version : N/A
vLLM Version : 0.1.dev1+gb4b9813 (git sha: b4b9813)
vLLM Build Flags:
CUDA Archs: 9.0a 10.0; ROCm: Disabled; Neuron: 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_VERSION=12.9.1
LD_LIBRARY_PATH=/opt/nvshmem-3.3.9/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
MAX_JOBS=128
NCCL_CROSS_NIC=0
NCCL_DEBUG=INFO
NCCL_IB_ADAPTIVE_ROUTING=1
NCCL_IB_FIFO_TC=84
NCCL_IB_GID_INDEX=3
NCCL_IB_QPS_PER_CONNECTION=4
NCCL_IB_TC=52
NCCL_NET_GDR_LEVEL=PIX
NCCL_NET_PLUGIN=/usr/local/gib/lib64/libnccl-net_internal.so
NCCL_NVLS_CHUNKSIZE=524288
NCCL_P2P_NET_CHUNKSIZE=131072
NCCL_P2P_NVL_CHUNKSIZE=524288
NCCL_P2P_PCI_CHUNKSIZE=131072
NCCL_TUNER_CONFIG_PATH=/usr/local/gib/configs/tuner_config_a4.txtpb
NCCL_VERSION=2.27.3-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_GDRCOPY=disabled
NVIDIA_PRODUCT_NAME=CUDA
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
NVIDIA_VISIBLE_DEVICES=all
TORCH_CUDA_ARCH_LIST=9.0a 10.0
VLLM_ALL2ALL_BACKEND=deepep_low_latency
VLLM_LOGGING_LEVEL=DEBUG
VLLM_NIXL_SIDE_CHANNEL_HOST=10.4.2.43
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_TRTLLM_DECODE_ATTENTION=1
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
Starting vllm on B200 against HEAD with:
$ vllm serve Qwen/Qwen3-30B-A3B-FP8 --port 8000 --enforce-eager --disable-log-requests --enable-expert-parallel --tensor-parallel-size 1 --data-parallel-size 2 --trust-remote-code
results in the following crash when attempting to serve a request.
(EngineCore_0 pid=6088) Traceback (most recent call last):
(EngineCore_0 pid=6088) File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_0 pid=6088) self.run()
(EngineCore_0 pid=6088) File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
(EngineCore_0 pid=6088) self._target(*self._args, **self._kwargs)
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 687, in run_engine_core
(EngineCore_0 pid=6088) raise e
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 676, in run_engine_core
(EngineCore_0 pid=6088) engine_core.run_busy_loop()
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 1017, in run_busy_loop
(EngineCore_0 pid=6088) executed = self._process_engine_step()
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 728, in _process_engine_step
(EngineCore_0 pid=6088) outputs, model_executed = self.step_fn()
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 273, in step
(EngineCore_0 pid=6088) model_output = self.execute_model_with_error_logging(
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 259, in execute_model_with_error_logging
(EngineCore_0 pid=6088) raise err
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/engine/core.py", line 250, in execute_model_with_error_logging
(EngineCore_0 pid=6088) return model_fn(scheduler_output)
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/executor/abstract.py", line 87, in execute_model
(EngineCore_0 pid=6088) output = self.collective_rpc("execute_model",
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
(EngineCore_0 pid=6088) answer = run_method(self.driver_worker, method, args, kwargs)
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/utils/__init__.py", line 2948, in run_method
(EngineCore_0 pid=6088) return func(*args, **kwargs)
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(EngineCore_0 pid=6088) return func(*args, **kwargs)
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/worker/gpu_worker.py", line 362, in execute_model
(EngineCore_0 pid=6088) output = self.model_runner.execute_model(scheduler_output,
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(EngineCore_0 pid=6088) return func(*args, **kwargs)
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/worker/gpu_model_runner.py", line 1484, in execute_model
(EngineCore_0 pid=6088) self._prepare_inputs(scheduler_output))
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/worker/gpu_model_runner.py", line 851, in _prepare_inputs
(EngineCore_0 pid=6088) attn_metadata_i = (builder.build(
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/v1/attention/backends/flashinfer.py", line 529, in build
(EngineCore_0 pid=6088) and use_trtllm_attention(
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/utils/flashinfer.py", line 165, in use_trtllm_attention
(EngineCore_0 pid=6088) env_value = envs.VLLM_USE_TRTLLM_ATTENTION
(EngineCore_0 pid=6088) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=6088) File "/app/vllm/vllm/envs.py", line 1089, in __getattr__
(EngineCore_0 pid=6088) raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
(EngineCore_0 pid=6088) AttributeError: module 'vllm.envs' has no attribute 'VLLM_USE_TRTLLM_ATTENTION'. Did you mean: 'VLLM_USE_TRTLLM_DECODE_ATTENTION'?
Looking at the source, #22095 did not add it to vllm.envs.
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.