vllm - 💡(How to fix) Fix [Bug]: Qwen3.5-2B output content is always None on RTX5090 [3 comments, 2 participants]

vllm2026-03-20 09:09:56

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#37663•Fetched 2026-04-08 01:04:14

View on GitHub

Comments

Participants

Timeline

Reactions

Author

yanghui1-arch

Participants

Nevermetyou65

yanghui1-arch

Timeline (top)

commented ×3closed ×1labeled ×1

Fix Action

Fix / Workaround

============================== 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): 208 On-line CPU(s) list: 0-207 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8470Q CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 52 Socket(s): 2 Stepping: 8 Frequency boost: enabled CPU max MHz: 2101.0000 CPU min MHz: 800.0000 BogoMIPS: 4200.00 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 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 invpcid_single intel_ppin cdp_l2 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 4.9 MiB (104 instances) L1i cache: 3.3 MiB (104 instances) L2 cache: 208 MiB (104 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-51,104-155 NUMA node1 CPU(s): 52-103,156-207 Vulnerability Gather data sampling: 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 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

Code Example

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                : Could not collect
CMake version                : version 4.2.3
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:46:43) [GCC 11.2.0] (64-bit runtime)
Python platform              : Linux-5.15.0-94-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.8.93
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : GPU 0: NVIDIA GeForce RTX 5090
Nvidia driver version        : 580.76.05
cuDNN version                : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
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):                             208
On-line CPU(s) list:                0-207
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8470Q
CPU family:                         6
Model:                              143
Thread(s) per core:                 2
Core(s) per socket:                 52
Socket(s):                          2
Stepping:                           8
Frequency boost:                    enabled
CPU max MHz:                        2101.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4200.00
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 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 invpcid_single intel_ppin cdp_l2 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          4.9 MiB (104 instances)
L1i cache:                          3.3 MiB (104 instances)
L2 cache:                           208 MiB (104 instances)
L3 cache:                           210 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-51,104-155
NUMA node1 CPU(s):                  52-103,156-207
Vulnerability Gather data sampling: 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 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==0.6.6
[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==1.18.0
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==26.4.0
[pip3] torch==2.10.0+cu128
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu128
[pip3] torchvision==0.25.0+cu128
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] flashinfer-python         0.6.6                    pypi_0    pypi
[conda] numpy                     2.2.6                    pypi_0    pypi
[conda] nvidia-cublas-cu12        12.8.4.1                 pypi_0    pypi
[conda] nvidia-cuda-cupti-cu12    12.8.90                  pypi_0    pypi
[conda] nvidia-cuda-nvrtc-cu12    12.8.93                  pypi_0    pypi
[conda] nvidia-cuda-runtime-cu12  12.8.90                  pypi_0    pypi
[conda] nvidia-cudnn-cu12         9.10.2.21                pypi_0    pypi
[conda] nvidia-cudnn-frontend     1.18.0                   pypi_0    pypi
[conda] nvidia-cufft-cu12         11.3.3.83                pypi_0    pypi
[conda] nvidia-cufile-cu12        1.13.1.3                 pypi_0    pypi
[conda] nvidia-curand-cu12        10.3.9.90                pypi_0    pypi
[conda] nvidia-cusolver-cu12      11.7.3.90                pypi_0    pypi
[conda] nvidia-cusparse-cu12      12.5.8.93                pypi_0    pypi
[conda] nvidia-cusparselt-cu12    0.7.1                    pypi_0    pypi
[conda] nvidia-cutlass-dsl        4.4.2                    pypi_0    pypi
[conda] nvidia-cutlass-dsl-libs-base 4.4.2                    pypi_0    pypi
[conda] nvidia-ml-py              13.595.45                pypi_0    pypi
[conda] nvidia-nccl-cu12          2.27.5                   pypi_0    pypi
[conda] nvidia-nvjitlink-cu12     12.8.93                  pypi_0    pypi
[conda] nvidia-nvshmem-cu12       3.4.5                    pypi_0    pypi
[conda] nvidia-nvtx-cu12          12.8.90                  pypi_0    pypi
[conda] pyzmq                     26.4.0                   pypi_0    pypi
[conda] torch                     2.10.0+cu128             pypi_0    pypi
[conda] torch-c-dlpack-ext        0.1.5                    pypi_0    pypi
[conda] torchaudio                2.10.0+cu128             pypi_0    pypi
[conda] torchvision               0.25.0+cu128             pypi_0    pypi
[conda] transformers              4.57.6                   pypi_0    pypi
[conda] triton                    3.6.0                    pypi_0    pypi

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.2rc1.dev56+gfad09e8a1.d20260320 (git sha: fad09e8a1, date: 20260320)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      52-103,156-207  1               N/A

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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-dae9c519-c575-a230-1163-beaedbee00ec
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
NCCL_VERSION=2.25.1-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility,graphics,video
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.8.1
LD_LIBRARY_PATH=/usr/local/cuda/lib64
OMP_NUM_THREADS=25
MKL_NUM_THREADS=25
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

---

from openai import OpenAI
import time, json

PROMPT_TEMPLATE = "Tell me the result. Just return final response not output other things. {text}"
items = [
    {"text": "Tell me who you are"},
    {"text": "7+2"},
    {"text": "8+2"},
    {"text": "9+2"},
    {"text": "11+2"},
    {"text": "12+2"},
    {"text": "34+2"},
]

MODEL = "Qwen/Qwen3.5-2B"

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="dummy",  # vLLM doesn't require a real key
)

print(f"Starting generation for {len(items)} messages...")
t0 = time.time()

results = []
for item in items:
    response = client.chat.completions.create(
        model=MODEL,
        messages=[{"role": "user", "content": PROMPT_TEMPLATE.format(text=item["text"])}],
        temperature=1.0,
        top_p=0.95,
        max_tokens=2048,
    )
    print()
    print(response)
    print()
    results.append({
        "item": item,
        "response": response.choices[0].message.content,
    })

elapsed = time.time() - t0
print(f"Generation complete: {elapsed:.1f}s ({len(items)/elapsed:.1f} items/sec)")

with open("./debug_outputs.json", "w") as f:
    json.dump(results, f, indent=2)
print("Wrote results to debug_outputs.json")

---

(base) root@autodl-container-65f24387ad-3113d861:~/autodl-tmp/garbled_output# python main.py 
Starting generation for 7 messages...

ChatCompletion(id='chatcmpl-9815834f958cdf4f', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning="I am Qwen3.5, a large multimodal language model developed by Alibaba Cloud. I excel across a vast spectrum of tasks, including complex reasoning, deep content creation, autonomous agent planning, and in-depth visual analysis. My capabilities span multilingual support with fluent interaction in 100+ languages, high-precision OCR, advanced programming integrations, long-context window handling up to 256K tokens, real-time graph understanding, specialized scientific computing, and intelligent full-stack code generation. Whether you need creative assistance, technical problem-solving, or data-driven insights, I'm equipped to deliver precise and comprehensive results. How can I assist you today?"), stop_reason=None, token_ids=None)], created=1773995893, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=135, prompt_tokens=31, total_tokens=166, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b049c8a85e5a254b', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='9'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=2, prompt_tokens=30, total_tokens=32, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b71dd6457507388f', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='10'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=30, total_tokens=33, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-94cf23ad90a4d582', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='11'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=30, total_tokens=33, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-aa6e5eb97277da35', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='13'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-a045c9c7f7ab2194', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='14'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b6c41e455f5ed7e2', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='36'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)

Generation complete: 3.7s (1.9 items/sec)
Wrote results to debug_outputs.json

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

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                : Could not collect
CMake version                : version 4.2.3
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:46:43) [GCC 11.2.0] (64-bit runtime)
Python platform              : Linux-5.15.0-94-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.8.93
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : GPU 0: NVIDIA GeForce RTX 5090
Nvidia driver version        : 580.76.05
cuDNN version                : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
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):                             208
On-line CPU(s) list:                0-207
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8470Q
CPU family:                         6
Model:                              143
Thread(s) per core:                 2
Core(s) per socket:                 52
Socket(s):                          2
Stepping:                           8
Frequency boost:                    enabled
CPU max MHz:                        2101.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4200.00
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 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 invpcid_single intel_ppin cdp_l2 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          4.9 MiB (104 instances)
L1i cache:                          3.3 MiB (104 instances)
L2 cache:                           208 MiB (104 instances)
L3 cache:                           210 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-51,104-155
NUMA node1 CPU(s):                  52-103,156-207
Vulnerability Gather data sampling: 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 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==0.6.6
[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==1.18.0
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==26.4.0
[pip3] torch==2.10.0+cu128
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu128
[pip3] torchvision==0.25.0+cu128
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] flashinfer-python         0.6.6                    pypi_0    pypi
[conda] numpy                     2.2.6                    pypi_0    pypi
[conda] nvidia-cublas-cu12        12.8.4.1                 pypi_0    pypi
[conda] nvidia-cuda-cupti-cu12    12.8.90                  pypi_0    pypi
[conda] nvidia-cuda-nvrtc-cu12    12.8.93                  pypi_0    pypi
[conda] nvidia-cuda-runtime-cu12  12.8.90                  pypi_0    pypi
[conda] nvidia-cudnn-cu12         9.10.2.21                pypi_0    pypi
[conda] nvidia-cudnn-frontend     1.18.0                   pypi_0    pypi
[conda] nvidia-cufft-cu12         11.3.3.83                pypi_0    pypi
[conda] nvidia-cufile-cu12        1.13.1.3                 pypi_0    pypi
[conda] nvidia-curand-cu12        10.3.9.90                pypi_0    pypi
[conda] nvidia-cusolver-cu12      11.7.3.90                pypi_0    pypi
[conda] nvidia-cusparse-cu12      12.5.8.93                pypi_0    pypi
[conda] nvidia-cusparselt-cu12    0.7.1                    pypi_0    pypi
[conda] nvidia-cutlass-dsl        4.4.2                    pypi_0    pypi
[conda] nvidia-cutlass-dsl-libs-base 4.4.2                    pypi_0    pypi
[conda] nvidia-ml-py              13.595.45                pypi_0    pypi
[conda] nvidia-nccl-cu12          2.27.5                   pypi_0    pypi
[conda] nvidia-nvjitlink-cu12     12.8.93                  pypi_0    pypi
[conda] nvidia-nvshmem-cu12       3.4.5                    pypi_0    pypi
[conda] nvidia-nvtx-cu12          12.8.90                  pypi_0    pypi
[conda] pyzmq                     26.4.0                   pypi_0    pypi
[conda] torch                     2.10.0+cu128             pypi_0    pypi
[conda] torch-c-dlpack-ext        0.1.5                    pypi_0    pypi
[conda] torchaudio                2.10.0+cu128             pypi_0    pypi
[conda] torchvision               0.25.0+cu128             pypi_0    pypi
[conda] transformers              4.57.6                   pypi_0    pypi
[conda] triton                    3.6.0                    pypi_0    pypi

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.2rc1.dev56+gfad09e8a1.d20260320 (git sha: fad09e8a1, date: 20260320)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      52-103,156-207  1               N/A

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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-dae9c519-c575-a230-1163-beaedbee00ec
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
NCCL_VERSION=2.25.1-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility,graphics,video
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.8.1
LD_LIBRARY_PATH=/usr/local/cuda/lib64
OMP_NUM_THREADS=25
MKL_NUM_THREADS=25
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

</details>

🐛 Describe the bug

After running vllm serve, I write a python script to call Qwen3.5-2B with openai sdk. I find that the content is always None. The script to start Qwen3.5-2B is vllm serve Qwen/Qwen3.5-2B --tensor-parallel-size 1 --max-model-len 8192 --gpu-memory-utilization 0.8 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --enable-prefix-caching --enforce-eager

Python script:

from openai import OpenAI
import time, json

PROMPT_TEMPLATE = "Tell me the result. Just return final response not output other things. {text}"
items = [
    {"text": "Tell me who you are"},
    {"text": "7+2"},
    {"text": "8+2"},
    {"text": "9+2"},
    {"text": "11+2"},
    {"text": "12+2"},
    {"text": "34+2"},
]

MODEL = "Qwen/Qwen3.5-2B"

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="dummy",  # vLLM doesn't require a real key
)

print(f"Starting generation for {len(items)} messages...")
t0 = time.time()

results = []
for item in items:
    response = client.chat.completions.create(
        model=MODEL,
        messages=[{"role": "user", "content": PROMPT_TEMPLATE.format(text=item["text"])}],
        temperature=1.0,
        top_p=0.95,
        max_tokens=2048,
    )
    print()
    print(response)
    print()
    results.append({
        "item": item,
        "response": response.choices[0].message.content,
    })

elapsed = time.time() - t0
print(f"Generation complete: {elapsed:.1f}s ({len(items)/elapsed:.1f} items/sec)")

with open("./debug_outputs.json", "w") as f:
    json.dump(results, f, indent=2)
print("Wrote results to debug_outputs.json")

Output:

(base) root@autodl-container-65f24387ad-3113d861:~/autodl-tmp/garbled_output# python main.py 
Starting generation for 7 messages...

ChatCompletion(id='chatcmpl-9815834f958cdf4f', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning="I am Qwen3.5, a large multimodal language model developed by Alibaba Cloud. I excel across a vast spectrum of tasks, including complex reasoning, deep content creation, autonomous agent planning, and in-depth visual analysis. My capabilities span multilingual support with fluent interaction in 100+ languages, high-precision OCR, advanced programming integrations, long-context window handling up to 256K tokens, real-time graph understanding, specialized scientific computing, and intelligent full-stack code generation. Whether you need creative assistance, technical problem-solving, or data-driven insights, I'm equipped to deliver precise and comprehensive results. How can I assist you today?"), stop_reason=None, token_ids=None)], created=1773995893, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=135, prompt_tokens=31, total_tokens=166, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b049c8a85e5a254b', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='9'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=2, prompt_tokens=30, total_tokens=32, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b71dd6457507388f', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='10'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=30, total_tokens=33, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-94cf23ad90a4d582', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='11'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=30, total_tokens=33, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-aa6e5eb97277da35', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='13'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-a045c9c7f7ab2194', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='14'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)


ChatCompletion(id='chatcmpl-b6c41e455f5ed7e2', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning='36'), stop_reason=None, token_ids=None)], created=1773995896, model='Qwen/Qwen3.5-2B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=3, prompt_tokens=31, total_tokens=34, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, prompt_token_ids=None, kv_transfer_params=None)

Generation complete: 3.7s (1.9 items/sec)
Wrote results to debug_outputs.json

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.

extent analysis

Fix Plan

The issue seems to be related to the content field being None in the response from the Qwen3.5-2B model. To fix this, we need to modify the Python script to handle the response correctly.

Here are the steps to fix the issue:

Check the response structure: The response from the Qwen3.5-2B model has a choices field that contains a list of Choice objects. Each Choice object has a message field that contains a ChatCompletionMessage object. The content field is inside the ChatCompletionMessage object.
Modify the script to handle the response: We need to modify the script to access the content field correctly.

Here is an example of how to modify the script:

response = client.chat.completions.create(
    model=MODEL,
    messages=[{"role": "user", "content": PROMPT_TEMPLATE.format(text=item["text"])}],
    temperature=1.0,
    top_p=0.95,
    max_tokens=2048,
)

# Access the content field correctly
content = response.choices[0].message.content

# If content is None, try to access the reasoning field
if content is None:
    content = response.choices[0].message.reasoning

results.append({
    "item": item,
    "response": content,
})

By modifying the script to handle the response correctly, we should be able to get the correct content from the Qwen3.5-2B model.

Verification

To verify that the fix worked, we can run the modified script and check the output. The output should contain the correct content from the Qwen3.5-2B model.

Extra Tips

Make sure to check the response structure and access the fields correctly.
If the content is still None, try to access other fields such as reasoning to see if they contain the expected output.
If the issue persists, try to debug the script and check the response from the Qwen3.5-2B model to see if it contains any errors or unexpected output.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #prompt formatting #chain error #conversation history #environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

vllm - 💡(How to fix) Fix [Bug]: Qwen3.5-2B output content is always None on RTX5090 [3 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: Qwen3.5-2B output content is always None on RTX5090 [3 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING