Your current environment

Collecting environment information...

============================== System Info

OS : Ubuntu 22.04.5 LTS (x86_64) GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version : Could not collect CMake version : version 3.22.1 Libc version : glibc-2.35

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

PyTorch version : 2.11.0+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 : 3.12.13 (main, Mar 4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime) Python platform : Linux-6.8.0-107-generic-x86_64-with-glibc2.35

============================== CUDA / GPU Info

Is CUDA available : True CUDA runtime version : 13.0.88 CUDA_MODULE_LOADING set to : GPU models and configuration : GPU 0: NVIDIA L4 Nvidia driver version : 580.126.20 cuDNN version : Could not collect HIP runtime version : N/A MIOpen runtime version : N/A Is XNNPACK available : True

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

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 48 On-line CPU(s) list: 0-47 Vendor ID: AuthenticAMD Model name: AMD EPYC 9254 24-Core Processor CPU family: 25 Model: 17 Thread(s) per core: 2 Core(s) per socket: 24 Socket(s): 1 Stepping: 1 Frequency boost: enabled CPU max MHz: 4153.1890 CPU min MHz: 1500.0000 BogoMIPS: 5790.83 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 amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 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 perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap ibpb_exit_to_user Virtualization: AMD-V L1d cache: 768 KiB (24 instances) L1i cache: 768 KiB (24 instances) L2 cache: 24 MiB (24 instances) L3 cache: 128 MiB (4 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-47 Vulnerability Gather data sampling: Not affected Vulnerability Indirect target selection: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Mitigation; Safe RET Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsa: Vulnerable: Clear CPU buffers attempted, no microcode Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

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

[pip3] flashinfer-python==0.6.12 [pip3] numpy==2.4.6 [pip3] nvidia-cublas==13.1.0.3 [pip3] nvidia-cuda-cccl==13.3.3.3.1 [pip3] nvidia-cuda-crt==13.3.33 [pip3] nvidia-cuda-cupti==13.0.85 [pip3] nvidia-cuda-nvcc==13.2.78 [pip3] nvidia-cuda-nvrtc==13.0.88 [pip3] nvidia-cuda-runtime==13.0.96 [pip3] nvidia-cuda-tileiras==13.2.78 [pip3] nvidia-cudnn-cu13==9.19.0.56 [pip3] nvidia-cudnn-frontend==1.24.1 [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==0.8.0 [pip3] nvidia-cutlass-dsl==4.5.2 [pip3] nvidia-cutlass-dsl-libs-base==4.5.2 [pip3] nvidia-cutlass-dsl-libs-cu13==4.5.2 [pip3] nvidia-ml-py==13.610.43 [pip3] nvidia-nccl-cu13==2.28.9 [pip3] nvidia-nvjitlink==13.0.88 [pip3] nvidia-nvshmem-cu13==3.4.5 [pip3] nvidia-nvtx==13.0.85 [pip3] nvidia-nvvm==13.2.78 [pip3] pyzmq==27.1.0 [pip3] tokenspeed-triton==3.7.10.post20260531 [pip3] torch==2.11.0 [pip3] torch_c_dlpack_ext==0.1.5 [pip3] torchaudio==2.11.0 [pip3] torchvision==0.26.0 [pip3] transformers==5.10.0.dev0 [pip3] triton==3.6.0 [conda] Could not collect

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

ROCM Version : Could not collect vLLM Version : 0.22.1rc1.dev307+g3e8afdf78 (git sha: 3e8afdf78) vLLM Build Flags: CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled GPU Topology: GPU0 NIC0 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NODE 0-47 0 N/A NIC0 NODE X

Legend:

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

NIC Legend:

NIC0: mlx5_bond_0

============================== Environment Variables

NVIDIA_VISIBLE_DEVICES=void NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536 NCCL_VERSION=2.21.5-1 NVIDIA_DRIVER_CAPABILITIES=compute,display,graphics,utility,video NVIDIA_PRODUCT_NAME=CUDA CUDA_VERSION=12.4.1 LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_CTK_LIBCUDA_DIR=/usr/lib/x86_64-linux-gnu PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

🐛 Describe the bug

while trying to running gemma 12b w4a16 error appears:

command: vllm serve google/gemma-4-12B-it-qat-w4a16-ct output: (APIServer pid=14189) AttributeError: 'Gemma4UnifiedVisionConfig' object has no attribute 'num_soft_tokens'

details

vllm serve google/gemma-4-12B-it-qat-w4a16-ct (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] █ █ █▄ ▄█ (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.22.1rc1.dev307+g3e8afdf78 (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] █▄█▀ █ █ █ █ model google/gemma-4-12B-it-qat-w4a16-ct (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀ (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:339] (APIServer pid=14189) INFO 06-09 16:12:18 [api_utils.py:273] non-default args: {'model_tag': 'google/gemma-4-12B-it-qat-w4a16-ct', 'model': 'google/gemma-4-12B-it-qat-w4a16-ct'} (APIServer pid=14189) Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. (APIServer pid=14189) INFO 06-09 16:12:20 [model.py:611] Resolved architecture: Gemma4UnifiedForConditionalGeneration (APIServer pid=14189) INFO 06-09 16:12:20 [model.py:1745] Using max model len 262144 (APIServer pid=14189) WARNING 06-09 16:12:54 [arg_utils.py:2477] Failed to determine min multimodal batched tokens: 'Gemma4UnifiedVisionConfig' object has no attribute 'num_soft_tokens' (APIServer pid=14189) INFO 06-09 16:12:54 [config.py:100] Gemma4 model has heterogeneous head dimensions (head_dim=256, global_head_dim=512). Forcing TRITON_ATTN backend to prevent mixed-backend numerical divergence. (APIServer pid=14189) INFO 06-09 16:12:54 [vllm.py:999] Asynchronous scheduling is enabled. (APIServer pid=14189) INFO 06-09 16:12:54 [kernel.py:270] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']) (APIServer pid=14189) WARNING 06-09 16:12:54 [cuda.py:243] Forcing --disable_chunked_mm_input for models with multimodal-bidirectional attention. (APIServer pid=14189) Traceback (most recent call last): (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/bin/vllm", line 10, in <module> (APIServer pid=14189) sys.exit(main()) (APIServer pid=14189) ^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 95, in main (APIServer pid=14189) args.dispatch_function(args) (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 148, in cmd (APIServer pid=14189) uvloop.run(run_server(args)) (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/uvloop/init.py", line 96, in run (APIServer pid=14189) return __asyncio.run( (APIServer pid=14189) ^^^^^^^^^^^^^^ (APIServer pid=14189) File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run (APIServer pid=14189) return runner.run(main) (APIServer pid=14189) ^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run (APIServer pid=14189) return self._loop.run_until_complete(task) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/uvloop/init.py", line 48, in wrapper (APIServer pid=14189) return await main (APIServer pid=14189) ^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 665, in run_server (APIServer pid=14189) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs) (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 679, in run_server_worker (APIServer pid=14189) async with build_async_engine_client( (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=14189) return await anext(self.gen) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 99, in build_async_engine_client (APIServer pid=14189) async with build_async_engine_client_from_engine_args( (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=14189) return await anext(self.gen) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 135, in build_async_engine_client_from_engine_args (APIServer pid=14189) async_llm = AsyncLLM.from_vllm_config( (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 217, in from_vllm_config (APIServer pid=14189) return cls( (APIServer pid=14189) ^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 135, in init (APIServer pid=14189) self.input_processor = InputProcessor(self.vllm_config, renderer) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/v1/engine/input_processor.py", line 62, in init (APIServer pid=14189) mm_budget = MultiModalBudget(vllm_config, mm_registry) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/multimodal/encoder_budget.py", line 87, in init (APIServer pid=14189) all_mm_max_toks_per_item = get_mm_max_toks_per_item( (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/multimodal/encoder_budget.py", line 25, in get_mm_max_toks_per_item (APIServer pid=14189) max_tokens_per_item = processor.info.get_mm_max_tokens_per_item( (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/vllm/model_executor/models/gemma4_unified.py", line 166, in get_mm_max_tokens_per_item (APIServer pid=14189) tokens_per_image = config.vision_config.num_soft_tokens (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) File "/workspace/Cairoai/.venv-vllm/lib/python3.12/site-packages/transformers/configuration_utils.py", line 434, in getattribute (APIServer pid=14189) return super().getattribute(key) (APIServer pid=14189) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=14189) AttributeError: 'Gemma4UnifiedVisionConfig' object has no attribute 'num_soft_tokens'

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.