vllm - 💡(How to fix) Fix [Bug]: Gemma 4 offline inference outputs gibberish [2 comments, 2 participants]

vllm2026-04-08 04:00:27

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#39265•Fetched 2026-04-09 07:52:14

View on GitHub

Comments

Participants

Timeline

Reactions

Author

tayweekiam

Participants

kimtajin

tayweekiam

Timeline (top)

commented ×2closed ×1labeled ×1

Fix Action

Fix / Workaround

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

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 43 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 256 On-line CPU(s) list: 0-255 Vendor ID: AuthenticAMD Model name: AMD EPYC 7742 64-Core Processor CPU family: 23 Model: 49 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 0 Frequency boost: enabled CPU max MHz: 2250.0000 CPU min MHz: 1500.0000 BogoMIPS: 4491.51 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca sme sev sev_es Virtualization: AMD-V L1d cache: 4 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 64 MiB (128 instances) L3 cache: 512 MiB (32 instances) NUMA node(s): 8 NUMA node0 CPU(s): 0-15,128-143 NUMA node1 CPU(s): 16-31,144-159 NUMA node2 CPU(s): 32-47,160-175 NUMA node3 CPU(s): 48-63,176-191 NUMA node4 CPU(s): 64-79,192-207 NUMA node5 CPU(s): 80-95,208-223 NUMA node6 CPU(s): 96-111,224-239 NUMA node7 CPU(s): 112-127,240-255 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: Vulnerable 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; Retpolines; IBPB conditional; IBRS_FW; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Code Example

==============================
        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-5.4.0-216-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 A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB

Nvidia driver version        : 535.261.03
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:                      43 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             256
On-line CPU(s) list:                0-255
Vendor ID:                          AuthenticAMD
Model name:                         AMD EPYC 7742 64-Core Processor
CPU family:                         23
Model:                              49
Thread(s) per core:                 2
Core(s) per socket:                 64
Socket(s):                          2
Stepping:                           0
Frequency boost:                    enabled
CPU max MHz:                        2250.0000
CPU min MHz:                        1500.0000
BogoMIPS:                           4491.51
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca sme sev sev_es
Virtualization:                     AMD-V
L1d cache:                          4 MiB (128 instances)
L1i cache:                          4 MiB (128 instances)
L2 cache:                           64 MiB (128 instances)
L3 cache:                           512 MiB (32 instances)
NUMA node(s):                       8
NUMA node0 CPU(s):                  0-15,128-143
NUMA node1 CPU(s):                  16-31,144-159
NUMA node2 CPU(s):                  32-47,160-175
NUMA node3 CPU(s):                  48-63,176-191
NUMA node4 CPU(s):                  64-79,192-207
NUMA node5 CPU(s):                  80-95,208-223
NUMA node6 CPU(s):                  96-111,224-239
NUMA node7 CPU(s):                  112-127,240-255
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:             Vulnerable
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; Retpolines; IBPB conditional; IBRS_FW; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[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==1.18.0
[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==4.4.2
[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==12.9.86
[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==5.5.0
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.2rc1.dev73+gdb7a17ecc (git sha: db7a17ecc)
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    NIC8    NIC9    NIC10   NIC11CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV12    NV12    NV12    SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS 16-31,144-159    1               N/A
GPU1    NV12     X      NV12    NV12    SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS 112-127,240-255  7               N/A
GPU2    NV12    NV12     X      NV12    SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS 112-127,240-255  7               N/A
GPU3    NV12    NV12    NV12     X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS 80-95,208-223    5               N/A
NIC0    SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC1    SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC2    PXB     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC3    PXB     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC4    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PIX     SYS     SYS     SYS     SYS     SYS     SYS
NIC5    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PIX      X      SYS     SYS     SYS     SYS     SYS     SYS
NIC6    SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS
NIC7    SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS
NIC8    SYS     SYS     SYS     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS
NIC9    SYS     SYS     SYS     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS
NIC10   SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PIX
NIC11   SYS     SYS     SYS     SYS     SYS     SYS     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
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5
  NIC6: mlx5_6
  NIC7: mlx5_7
  NIC8: mlx5_8
  NIC9: mlx5_9
  NIC10: mlx5_10
  NIC11: mlx5_11

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=3,4,5,6
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_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

---

from vllm import LLM, SamplingParams

if __name__ == "__main__":
        # --- Configuration ---
        MODEL_NAME = "/raid/models/gemma-4-31B-it"  # Change to your model
        MAX_TOKENS = 512
        TEMPERATURE = 0.7
        TOP_P = 0.95

        # --- Define prompts ---
        prompts = [
            "Explain quantum computing in simple terms.",
            "Write a short poem about the ocean.",
            "What are the main differences between Python and Rust?",
        ]

        # --- Set up sampling parameters ---
        sampling_params = SamplingParams(
            temperature=TEMPERATURE,
            top_p=TOP_P,
            max_tokens=MAX_TOKENS,
        )

        # --- Initialize the model ---
        llm = LLM(
            model=MODEL_NAME,
            trust_remote_code=True,       # Uncomment if the model requires it
            tensor_parallel_size=4,       # Uncomment for multi-GPU
            dtype="auto",                 # auto, float16, bfloat16
            gpu_memory_utilization=0.90,  # Fraction of GPU memory to use
            max_model_len=4096,           # Override max context length
        )

        # --- Run inference ---
        outputs = llm.generate(prompts, sampling_params)

        # --- Print results ---
        for output in outputs:
            prompt = output.prompt
            generated = output.outputs[0].text
            print(f"Prompt:    {prompt!r}")
            print(f"Response:  {generated}")
            print("-" * 60)

RAW_BUFFERClick to expand / collapse

Your current environment

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

==============================
        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-5.4.0-216-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 A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB

Nvidia driver version        : 535.261.03
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:                      43 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             256
On-line CPU(s) list:                0-255
Vendor ID:                          AuthenticAMD
Model name:                         AMD EPYC 7742 64-Core Processor
CPU family:                         23
Model:                              49
Thread(s) per core:                 2
Core(s) per socket:                 64
Socket(s):                          2
Stepping:                           0
Frequency boost:                    enabled
CPU max MHz:                        2250.0000
CPU min MHz:                        1500.0000
BogoMIPS:                           4491.51
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca sme sev sev_es
Virtualization:                     AMD-V
L1d cache:                          4 MiB (128 instances)
L1i cache:                          4 MiB (128 instances)
L2 cache:                           64 MiB (128 instances)
L3 cache:                           512 MiB (32 instances)
NUMA node(s):                       8
NUMA node0 CPU(s):                  0-15,128-143
NUMA node1 CPU(s):                  16-31,144-159
NUMA node2 CPU(s):                  32-47,160-175
NUMA node3 CPU(s):                  48-63,176-191
NUMA node4 CPU(s):                  64-79,192-207
NUMA node5 CPU(s):                  80-95,208-223
NUMA node6 CPU(s):                  96-111,224-239
NUMA node7 CPU(s):                  112-127,240-255
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:             Vulnerable
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; Retpolines; IBPB conditional; IBRS_FW; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[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==1.18.0
[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==4.4.2
[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==12.9.86
[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==5.5.0
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.2rc1.dev73+gdb7a17ecc (git sha: db7a17ecc)
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    NIC8    NIC9    NIC10   NIC11CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV12    NV12    NV12    SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS 16-31,144-159    1               N/A
GPU1    NV12     X      NV12    NV12    SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS 112-127,240-255  7               N/A
GPU2    NV12    NV12     X      NV12    SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS     SYS     SYS 112-127,240-255  7               N/A
GPU3    NV12    NV12    NV12     X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB     PXB     SYS     SYS 80-95,208-223    5               N/A
NIC0    SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC1    SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC2    PXB     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC3    PXB     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS
NIC4    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PIX     SYS     SYS     SYS     SYS     SYS     SYS
NIC5    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PIX      X      SYS     SYS     SYS     SYS     SYS     SYS
NIC6    SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS     SYS     SYS
NIC7    SYS     PXB     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS     SYS     SYS
NIC8    SYS     SYS     SYS     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PXB     SYS     SYS
NIC9    SYS     SYS     SYS     PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB      X      SYS     SYS
NIC10   SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      PIX
NIC11   SYS     SYS     SYS     SYS     SYS     SYS     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
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5
  NIC6: mlx5_6
  NIC7: mlx5_7
  NIC8: mlx5_8
  NIC9: mlx5_9
  NIC10: mlx5_10
  NIC11: mlx5_11

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=3,4,5,6
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_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

</details>

🐛 Describe the bug

I have used the docker image suggested in the Gemma 4 Usage Guide to perform offline inference (using the LLM class) with gemma-4-31B-it. However, it seems like it is outputting gibberish. This does not happen when the model is served via an OpenAI API server.

Any idea what could be the issue?

This is the script I used for offline inference:

from vllm import LLM, SamplingParams

if __name__ == "__main__":
        # --- Configuration ---
        MODEL_NAME = "/raid/models/gemma-4-31B-it"  # Change to your model
        MAX_TOKENS = 512
        TEMPERATURE = 0.7
        TOP_P = 0.95

        # --- Define prompts ---
        prompts = [
            "Explain quantum computing in simple terms.",
            "Write a short poem about the ocean.",
            "What are the main differences between Python and Rust?",
        ]

        # --- Set up sampling parameters ---
        sampling_params = SamplingParams(
            temperature=TEMPERATURE,
            top_p=TOP_P,
            max_tokens=MAX_TOKENS,
        )

        # --- Initialize the model ---
        llm = LLM(
            model=MODEL_NAME,
            trust_remote_code=True,       # Uncomment if the model requires it
            tensor_parallel_size=4,       # Uncomment for multi-GPU
            dtype="auto",                 # auto, float16, bfloat16
            gpu_memory_utilization=0.90,  # Fraction of GPU memory to use
            max_model_len=4096,           # Override max context length
        )

        # --- Run inference ---
        outputs = llm.generate(prompts, sampling_params)

        # --- Print results ---
        for output in outputs:
            prompt = output.prompt
            generated = output.outputs[0].text
            print(f"Prompt:    {prompt!r}")
            print(f"Response:  {generated}")
            print("-" * 60)

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

TL;DR

The issue with the model outputting gibberish during offline inference may be related to incorrect configuration or compatibility issues with the GPU or model, and verifying the model and environment settings is necessary.

Guidance

Verify that the MODEL_NAME path is correct and the model is properly downloaded and loaded.
Check the GPU configuration and ensure that the tensor_parallel_size and gpu_memory_utilization parameters are set correctly for the available GPU resources.
Test the model with a different set of prompts or a smaller model to isolate the issue.
Ensure that the trust_remote_code parameter is set correctly, as it may affect the model's behavior.
Review the environment variables, such as TORCH_CUDA_ARCH_LIST and NVIDIA_VISIBLE_DEVICES, to ensure they are set correctly for the GPU architecture and available devices.

Example

No specific code changes are suggested at this point, but the script provided can be modified to include additional logging or debugging statements to help identify the issue.

Notes

The issue may be related to the specific model or environment configuration, and further debugging or testing may be necessary to determine the root cause.

Recommendation

Apply workaround: Verify the model and environment settings, and test the model with different configurations to isolate the issue. If the problem persists, consider seeking additional support or guidance from the model developers or community.

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 #environment variable #memory leak #API versioning #request timeout

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]: Gemma 4 offline inference outputs gibberish [2 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

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: Gemma 4 offline inference outputs gibberish [2 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

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING