[Bug]: crash when sending wav to qwen3_omni_moe #26630
Description
Your current environment
The output of python collect_env.py
==============================
System Info
==============================
OS : Debian GNU/Linux 13 (trixie) (x86_64)
GCC version : (Debian 14.2.0-19) 14.2.0
Clang version : Could not collect
CMake version : Could not collect
Libc version : glibc-2.41
==============================
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 : 3.13.8 (main, Oct 7 2025, 20:55:24) [GCC 14.2.0] (64-bit runtime)
Python platform : Linux-5.4.0-42-generic-x86_64-with-glibc2.41
==============================
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 A30
GPU 1: NVIDIA A30
GPU 2: NVIDIA A30
GPU 3: NVIDIA A30
GPU 4: NVIDIA A30
GPU 5: NVIDIA A30
GPU 6: NVIDIA A30
GPU 7: NVIDIA A30
Nvidia driver version : 550.54.15
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): 64
On-line CPU(s) list: 0-55
Off-line CPU(s) list: 56-63
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 2
Stepping: 6
BogoMIPS: 4800.00
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 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 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 1.5 MiB (32 instances)
L1i cache: 1 MiB (32 instances)
L2 cache: 40 MiB (32 instances)
L3 cache: 48 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-15,32-47
NUMA node1 CPU(s): 16-31,48-63
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: 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
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.4.0
[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-cutlass-dsl==4.2.1
[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] pyzmq==27.1.0
[pip3] torch==2.8.0
[pip3] torchaudio==2.8.0
[pip3] torchvision==0.23.0
[pip3] transformers==4.57.0
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.4.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.11.0rc2.dev401+ge317414ce (git sha: e317414ce)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PIX PIX PIX SYS SYS SYS SYS SYS SYS 0-15,32-47 0 N/A
GPU1 PIX X PIX PIX SYS SYS SYS SYS SYS SYS 0-15,32-47 0 N/A
GPU2 PIX PIX X PIX SYS SYS SYS SYS SYS SYS 0-15,32-47 0 N/A
GPU3 PIX PIX PIX X SYS SYS SYS SYS SYS SYS 0-15,32-47 0 N/A
GPU4 SYS SYS SYS SYS X PIX PIX PIX SYS SYS 16-31,48-55 1 N/A
GPU5 SYS SYS SYS SYS PIX X PIX PIX SYS SYS 16-31,48-55 1 N/A
GPU6 SYS SYS SYS SYS PIX PIX X PIX SYS SYS 16-31,48-55 1 N/A
GPU7 SYS SYS SYS SYS PIX PIX PIX X SYS SYS 16-31,48-55 1 N/A
NIC0 SYS SYS SYS SYS SYS SYS SYS SYS X PIX
NIC1 SYS SYS SYS SYS SYS SYS SYS SYS 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=GPU-9956808a-9dc7-b4ce-d589-cb15f9d8eb98,GPU-9e5e1ec0-d466-5ef4-b38e-e35c505f69a0,GPU-6214ff3e-d839-4401-1853-5d44403ba34b,GPU-eeb690a6-147b-1363-250e-2aafd81dbf7a,GPU-006ee502-7656-fc17-3d3e-ee34abc6ff19,GPU-2f22ce7b-d790-daac-443b-59c77663a410,GPU-ea39f7d2-a867-4dfd-1f9c-be3abe99f543,GPU-6e437071-8785-ea9b-b169-ecd74fc07021
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
vllm serve /jr-sec-ai/open-models/Qwen/Qwen3-Omni-30B-A3B-Instruct --served-model-name Qwen3-Omni-30B-A3B-Instruct --dtype bfloat16 --max-model-len 65536 --allowed-local-media-path / -tp 8 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser hermes
POST /v1/chat/completions
{
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": [
{
"type": "audio_url",
"audio_url": {
"url": "https://freedata.oss-cn-beijing.aliyuncs.com/freedata/magicdatatech/MDT-ASR-E026/WAV/20200321_2P_mac_oppor15_gongsi_03702.wav"
}
},
{"type": "text", "text": "提取每个人说的话。"}
]}
]
}
It show the errors and exit
RuntimeError: split_with_sizes expects split_sizes to sum exactly to 3000 (input tensor's size at dimension 0), but got split_sizes=[100, 100, 100, 100...
Here is the full log:
error_log.txt
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.