Your current environment

Collecting environment information...

    System Info

============================== OS : Ubuntu 22.04.5 LTS (x86_64) GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0 Clang version : Could not collect CMake version : Could not collect Libc version : glibc-2.35

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

PyTorch version : 2.10.0+cu129 Is debug build : False CUDA used to build PyTorch : 12.9 ROCM used to build PyTorch : N/A

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

Python version : 3.12.13 (main, Mar 4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime) Python platform : Linux-6.8.0-101-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 B200 Nvidia driver version : 570.86.10 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): 288 On-line CPU(s) list: 0-287 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) 6960P CPU family: 6 Model: 173 Thread(s) per core: 2 Core(s) per socket: 72 Socket(s): 2 Stepping: 1 CPU max MHz: 3900.0000 CPU min MHz: 800.0000 BogoMIPS: 5400.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req 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 ibpb_exit_to_user Virtualization: VT-x L1d cache: 6.8 MiB (144 instances) L1i cache: 9 MiB (144 instances) L2 cache: 288 MiB (144 instances) L3 cache: 864 MiB (2 instances) NUMA node(s): 6 NUMA node0 CPU(s): 0-23,144-167 NUMA node1 CPU(s): 24-47,168-191 NUMA node2 CPU(s): 48-71,192-215 NUMA node3 CPU(s): 72-95,216-239 NUMA node4 CPU(s): 96-119,240-263 NUMA node5 CPU(s): 120-143,264-287 Vulnerability Gather data sampling: Not affected Vulnerability Indirect target selection: 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; PBRSB-eIBRS Not affected; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

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

[pip3] flashinfer-python==0.6.4 [pip3] numpy==2.2.6 [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==1.19.0 [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==4.4.1 [pip3] nvidia-cutlass-dsl-libs-base==4.4.1 [pip3] nvidia-ml-py==13.590.48 [pip3] nvidia-nccl-cu12==2.27.5 [pip3] nvidia-nvjitlink-cu12==12.9.86 [pip3] nvidia-nvshmem-cu12==3.4.5 [pip3] nvidia-nvtx-cu12==12.9.79 [pip3] pyzmq==27.1.0 [pip3] torch==2.10.0+cu129 [pip3] torch_c_dlpack_ext==0.1.5 [pip3] torchaudio==2.10.0+cu129 [pip3] torchvision==0.25.0+cu129 [pip3] transformers==4.57.6 [pip3] triton==3.6.0 [conda] Could not collect

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

ROCM Version : Could not collect vLLM Version : 0.17.0rc1.dev204+g04b67d8f6 (git sha: 04b67d8f6) vLLM Build Flags: CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled GPU Topology: GPU0 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X SYS SYS PIX NODE SYS SYS SYS SYS 48-71,192-215 2 N/A NIC0 SYS X NODE SYS SYS SYS SYS SYS SYS NIC1 SYS NODE X SYS SYS SYS SYS SYS SYS NIC2 PIX SYS SYS X NODE SYS SYS SYS SYS NIC3 NODE SYS SYS NODE X SYS SYS SYS SYS NIC4 SYS SYS SYS SYS SYS X NODE SYS SYS NIC5 SYS SYS SYS SYS SYS NODE X SYS SYS NIC6 SYS SYS SYS SYS SYS SYS SYS X NODE NIC7 SYS SYS SYS SYS SYS SYS SYS NODE 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_9 NIC6: mlx5_10 NIC7: mlx5_11

============================== 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 TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.9 9.0 10.0 12.0 NVIDIA_DRIVER_CAPABILITIES=compute,utility VLLM_USE_MODELSCOPE=True VLLM_USAGE_SOURCE=production-docker-image CUDA_VERSION=12.9.1 VLLM_ENABLE_CUDA_COMPATIBILITY=0 LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64 PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

🐛 Describe the bug

Hi, Qwen3.5-35B-A3B on B200 with vllm v0.17.0 output random result, but normal on A100.

docker run -d \
--gpus '"device=2"' \
-v /etc/localtime:/etc/localtime \
-v /mnt/data2/ai_deploy/models/pretrained/modelscope:/root/.cache/modelscope \
-e VLLM_USE_MODELSCOPE=True \
-p 9993:8000 \
--ipc=host \
--restart always \
--name Qwen3.5-35B-A3B \
vllm/vllm-openai:nightly \
--model /root/.cache/modelscope/hub/Qwen/Qwen3.5-35B-A3B-FP8 \
--served-model-name Qwen3.5-35B-A3B \
--port 8000 \
--max-num-seqs 128 \
--max-model-len 262144 \
--gpu-memory-utilization 0.45 \
--mm-encoder-tp-mode data \
--mm-processor-cache-type shm \
--reasoning-parser qwen3 \
--tensor-parallel-size 1 \
--disable-fastapi-docs \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'

The left one is on B200, another is on A100. <img width="1584" height="510" alt="Image" src="https://github.com/user-attachments/assets/d006e0ec-b5ad-4c42-b1fb-06bfd8ea1f99" />

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.