vllm - 💡(How to fix) Fix [Bug]: (Gemma 4 MoE) _compute_num_soft_tokens diverges from HF get_aspect_ratio_preserving_size [1 comments, 2 participants]

vllm2026-05-13 05:28:35

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#42485•Fetched 2026-05-14 03:29:49

View on GitHub

Comments

Participants

Timeline

Reactions

Author

itfwonjulee

Participants

itfwonjulee

skyloevil

Timeline (top)

mentioned ×2subscribed ×2commented ×1labeled ×1

Error Message

ValueError: Attempted to assign 529 + 280 multimodal tokens to 809 placeholders

Fix Action

Fix / Workaround

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

Architecture: aarch64 CPU op-mode(s): 64-bit Byte Order: Little Endian CPU(s): 20 On-line CPU(s) list: 0-19 Vendor ID: ARM BIOS Vendor ID: NVIDIA Model name: Cortex-X925 BIOS Model name: GB10 Unknown CPU @ 3.9GHz BIOS CPU family: 258 Model: 1 Thread(s) per core: 1 Core(s) per socket: 10 Socket(s): 1 Stepping: r0p1 Frequency boost: disabled CPU(s) scaling MHz: 100% CPU max MHz: 3900.0000 CPU min MHz: 1378.0000 BogoMIPS: 2000.00 Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt Model name: Cortex-A725 BIOS Model name: GB10 Unknown CPU @ 3.9GHz BIOS CPU family: 258 Model: 1 Thread(s) per core: 1 Core(s) per socket: 10 Socket(s): 1 Stepping: r0p1 CPU(s) scaling MHz: 100% CPU max MHz: 2808.0000 CPU min MHz: 338.0000 BogoMIPS: 2000.00 Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt L1d cache: 1.3 MiB (20 instances) L1i cache: 1.3 MiB (20 instances) L2 cache: 25 MiB (20 instances) L3 cache: 24 MiB (2 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-19 Vulnerability Gather data sampling: Not affected Vulnerability Ghostwrite: 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 Old microcode: 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; __user pointer sanitization Vulnerability Spectre v2: Mitigation; CSV2, BHB Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected

Concrete divergence at max_soft_tokens=280, patch_size=16, pooling_kernel_size=3:

from transformers.models.gemma4.image_processing_pil_gemma4 import get_aspect_ratio_preserving_size
target_h, target_w = get_aspect_ratio_preserving_size(
    height=image_height, width=image_width,
    patch_size=patch_size,
    max_patches=max_soft_tokens * pooling_kernel_size ** 2,
    pooling_kernel_size=pooling_kernel_size,
)
return ((target_h // patch_size) * (target_w // patch_size)) // (pooling_kernel_size ** 2)

Code Example

==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (aarch64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.12.0.dev20260405+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.17.0-1008-nvidia-aarch64-with-glibc2.39
    
==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.2.51
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : GPU 0: NVIDIA GB10
Nvidia driver version        : 580.126.09
cuDNN version                : Probably one of the following:
/usr/lib/aarch64-linux-gnu/libcudnn.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_adv.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_cnn.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_precompiled.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_graph.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_heuristic.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_ops.so.9.20.0
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  20
On-line CPU(s) list:                     0-19
Vendor ID:                               ARM
BIOS Vendor ID:                          NVIDIA
Model name:                              Cortex-X925
BIOS Model name:                         GB10 Unknown CPU @ 3.9GHz
BIOS CPU family:                         258
Model:                                   1
Thread(s) per core:                      1
Core(s) per socket:                      10
Socket(s):                               1
Stepping:                                r0p1
Frequency boost:                         disabled
CPU(s) scaling MHz:                      100%
CPU max MHz:                             3900.0000
CPU min MHz:                             1378.0000
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt
Model name:                              Cortex-A725
BIOS Model name:                         GB10 Unknown CPU @ 3.9GHz
BIOS CPU family:                         258
Model:                                   1
Thread(s) per core:                      1
Core(s) per socket:                      10
Socket(s):                               1
Stepping:                                r0p1
CPU(s) scaling MHz:                      100%
CPU max MHz:                             2808.0000
CPU min MHz:                             338.0000
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt
L1d cache:                               1.3 MiB (20 instances)
L1i cache:                               1.3 MiB (20 instances)
L2 cache:                                25 MiB (20 instances)
L3 cache:                                24 MiB (2 instances)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-19
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                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 Old microcode:             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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[pip3] numpy==2.2.6
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.20.0.48
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.1
[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-cu13==2.29.7
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] pyzmq==27.1.0
[pip3] torch==2.12.0.dev20260405+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0.dev20260402+cu130
[pip3] torchvision==0.27.0.dev20260405+cu130
[pip3] transformers==5.5.0
[pip3] triton==3.7.0+git9c288bc5
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1rc1.dev36+g9a528260e.d20260405 (git sha: 9a528260e, date: 20260405)
vLLM Build Flags:
  CUDA Archs: 12.1a; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	NIC0	NIC1	NIC2	NIC3	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NODE	NODE	NODE	NODE	0-19	0		N/A
NIC0	NODE	 X 	PIX	NODE	NODE				
NIC1	NODE	PIX	 X 	NODE	NODE				
NIC2	NODE	NODE	NODE	 X 	PIX				
NIC3	NODE	NODE	NODE	PIX	 X 				

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: rocep1s0f0
  NIC1: rocep1s0f1
  NIC2: roceP2p1s0f0
  NIC3: roceP2p1s0f1

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=13.2 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>=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 brand=unknown,driver>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581 brand=unknown,driver>=590,driver<591 brand=grid,driver>=590,driver<591 brand=tesla,driver>=590,driver<591 brand=nvidia,driver>=590,driver<591 brand=quadro,driver>=590,driver<591 brand=quadrortx,driver>=590,driver<591 brand=nvidiartx,driver>=590,driver<591 brand=vapps,driver>=590,driver<591 brand=vpc,driver>=590,driver<591 brand=vcs,driver>=590,driver<591 brand=vws,driver>=590,driver<591 brand=cloudgaming,driver>=590,driver<591
TORCH_CUDA_ARCH_LIST=12.1a
NCCL_SOCKET_IFNAME=
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NCCL_IB_HCA=
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=13.2.0
MAX_JOBS=16
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NCCL_IB_DISABLE=0
VLLM_HOST_IP=127.0.0.1
NCCL_IGNORE_CPU_AFFINITY=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

---

ValueError: Attempted to assign 529 + 280 multimodal tokens to 809 placeholders

---

from transformers.models.gemma4.image_processing_pil_gemma4 import get_aspect_ratio_preserving_size
target_h, target_w = get_aspect_ratio_preserving_size(
    height=image_height, width=image_width,
    patch_size=patch_size,
    max_patches=max_soft_tokens * pooling_kernel_size ** 2,
    pooling_kernel_size=pooling_kernel_size,
)
return ((target_h // patch_size) * (target_w // patch_size)) // (pooling_kernel_size ** 2)

RAW_BUFFERClick to expand / collapse

Your current environment

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

==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (aarch64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.12.0.dev20260405+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.17.0-1008-nvidia-aarch64-with-glibc2.39
    
==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.2.51
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : GPU 0: NVIDIA GB10
Nvidia driver version        : 580.126.09
cuDNN version                : Probably one of the following:
/usr/lib/aarch64-linux-gnu/libcudnn.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_adv.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_cnn.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_precompiled.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_graph.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_heuristic.so.9.20.0
/usr/lib/aarch64-linux-gnu/libcudnn_ops.so.9.20.0
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  20
On-line CPU(s) list:                     0-19
Vendor ID:                               ARM
BIOS Vendor ID:                          NVIDIA
Model name:                              Cortex-X925
BIOS Model name:                         GB10 Unknown CPU @ 3.9GHz
BIOS CPU family:                         258
Model:                                   1
Thread(s) per core:                      1
Core(s) per socket:                      10
Socket(s):                               1
Stepping:                                r0p1
Frequency boost:                         disabled
CPU(s) scaling MHz:                      100%
CPU max MHz:                             3900.0000
CPU min MHz:                             1378.0000
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt
Model name:                              Cortex-A725
BIOS Model name:                         GB10 Unknown CPU @ 3.9GHz
BIOS CPU family:                         258
Model:                                   1
Thread(s) per core:                      1
Core(s) per socket:                      10
Socket(s):                               1
Stepping:                                r0p1
CPU(s) scaling MHz:                      100%
CPU max MHz:                             2808.0000
CPU min MHz:                             338.0000
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti ecv afp wfxt
L1d cache:                               1.3 MiB (20 instances)
L1i cache:                               1.3 MiB (20 instances)
L2 cache:                                25 MiB (20 instances)
L3 cache:                                24 MiB (2 instances)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-19
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                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 Old microcode:             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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[pip3] numpy==2.2.6
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.20.0.48
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.1
[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-cu13==2.29.7
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] pyzmq==27.1.0
[pip3] torch==2.12.0.dev20260405+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0.dev20260402+cu130
[pip3] torchvision==0.27.0.dev20260405+cu130
[pip3] transformers==5.5.0
[pip3] triton==3.7.0+git9c288bc5
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1rc1.dev36+g9a528260e.d20260405 (git sha: 9a528260e, date: 20260405)
vLLM Build Flags:
  CUDA Archs: 12.1a; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	NIC0	NIC1	NIC2	NIC3	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NODE	NODE	NODE	NODE	0-19	0		N/A
NIC0	NODE	 X 	PIX	NODE	NODE				
NIC1	NODE	PIX	 X 	NODE	NODE				
NIC2	NODE	NODE	NODE	 X 	PIX				
NIC3	NODE	NODE	NODE	PIX	 X 				

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: rocep1s0f0
  NIC1: rocep1s0f1
  NIC2: roceP2p1s0f0
  NIC3: roceP2p1s0f1

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=13.2 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>=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 brand=unknown,driver>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581 brand=unknown,driver>=590,driver<591 brand=grid,driver>=590,driver<591 brand=tesla,driver>=590,driver<591 brand=nvidia,driver>=590,driver<591 brand=quadro,driver>=590,driver<591 brand=quadrortx,driver>=590,driver<591 brand=nvidiartx,driver>=590,driver<591 brand=vapps,driver>=590,driver<591 brand=vpc,driver>=590,driver<591 brand=vcs,driver>=590,driver<591 brand=vws,driver>=590,driver<591 brand=cloudgaming,driver>=590,driver<591
TORCH_CUDA_ARCH_LIST=12.1a
NCCL_SOCKET_IFNAME=
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NCCL_IB_HCA=
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=13.2.0
MAX_JOBS=16
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NCCL_IB_DISABLE=0
VLLM_HOST_IP=127.0.0.1
NCCL_IGNORE_CPU_AFFINITY=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

</details>

🐛 Describe the bug

Hi Team,

Thank you for your hard work.

Device: DGX Spark (GB10, single-node, 128GB RAM, running Gemma-4-26B-A4B-it-NVFP4A16) vLLM: 0.19.1rc1.dev36+g9a528260e, running via eugr/spark-vllm-docker

Gemma4ProcessingInfo._compute_num_soft_tokens() in vllm/model_executor/models/gemma4_mm.py is a re-implementation of HF's get_aspect_ratio_preserving_size() that omits HF's max_side_length clamp, so on extreme-aspect-ratio images (≥ ~30:1 — full-page receipt scans, stitched chat screenshots, leaderboards, vertical banners) vLLM emits more placeholders in the prompt than the encoder produces embeddings. _merge_multimodal_embeddings then asserts inside EngineCore, killing the engine and aborting every in-flight request:

ValueError: Attempted to assign 529 + 280 multimodal tokens to 809 placeholders

I believe @skyloevil semi-fixed the issue with PR #42217: the pixel_values contains inconsistent shapes TensorSchema/batching error is fixed and is working, but the verification script in that PR only uses images up to ~4.7:1 aspect ratio (1024×1024, 256×128, 1400×300, 300×1400), so the per-image count divergence wasn't exercised. The divergence only triggers when HF's target_h == 0 or target_w == 0 branch fires, at which point the vLLM formula has no upper bound and overshoots by up to ~1.9×.

Concrete divergence at max_soft_tokens=280, patch_size=16, pooling_kernel_size=3:

image (W×H)	vLLM `_compute_num_soft_tokens`	HF `get_aspect_ratio_preserving_size`
16×16000	529	280
10×10000	529	280
1×1000	529	280

I fixed the issue on my local copy by delegating to HF directly so the two paths agree by construction (also future-proof against any tweaks to the HF processor):

from transformers.models.gemma4.image_processing_pil_gemma4 import get_aspect_ratio_preserving_size
target_h, target_w = get_aspect_ratio_preserving_size(
    height=image_height, width=image_width,
    patch_size=patch_size,
    max_patches=max_soft_tokens * pooling_kernel_size ** 2,
    pooling_kernel_size=pooling_kernel_size,
)
return ((target_h // patch_size) * (target_w // patch_size)) // (pooling_kernel_size ** 2)

Tested in production against bg-digitalservices/Gemma-4-26B-A4B-it-NVFP4A16 on vLLM 0.19.1rc1.dev36+g9a528260e, DGX Spark single-node, TP=1, max_model_len=262144, max_num_seqs=64, at up to 200 concurrent mixed-aspect-ratio image requests — with this fix on top of #42217 the engine no longer crashes.

Appreciate any feedback. Thanks.

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.

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?

#tokenizer error #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]: (Gemma 4 MoE) _compute_num_soft_tokens diverges from HF get_aspect_ratio_preserving_size [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: (Gemma 4 MoE) _compute_num_soft_tokens diverges from HF get_aspect_ratio_preserving_size [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

Still need to ship something?

RELATED_DISCOVERY

TRENDING