vllm: [Bug]: Gemma3 Offline Batch Inference: Attempted to assign XXX multimodal tokens to YYY placeholders
Your current environment
The output of `python collect_env.py`
Collecting environment information...
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04 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
Python version: 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-5.15.0-112-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version: 550.90.07
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 104
On-line CPU(s) list: 0-103
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8470
CPU family: 6
Model: 143
Thread(s) per core: 1
Core(s) per socket: 52
Socket(s): 2
Stepping: 8
BogoMIPS: 4000.00
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 monitor ds_cpl 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 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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
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): 8
NUMA node0 CPU(s): 0-12
NUMA node1 CPU(s): 13-25
NUMA node2 CPU(s): 26-38
NUMA node3 CPU(s): 39-51
NUMA node4 CPU(s): 52-64
NUMA node5 CPU(s): 65-77
NUMA node6 CPU(s): 78-90
NUMA node7 CPU(s): 91-103
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; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] flashinfer-python==0.2.3+cu124torch2.6
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-ml-py==12.570.86
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pynvml==12.0.0
[pip3] pyzmq==26.3.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.50.0.dev0
[pip3] triton==3.2.0
[conda] flashinfer-python 0.2.3+cu124torch2.6 pypi_0 pypi
[conda] numpy 1.26.4 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.4.5.8 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.2.1.3 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.5.147 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.6.1.9 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.3.1.170 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.6.2 pypi_0 pypi
[conda] nvidia-ml-py 12.570.86 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.4.127 pypi_0 pypi
[conda] pynvml 12.0.0 pypi_0 pypi
[conda] pyzmq 26.3.0 pypi_0 pypi
[conda] torch 2.6.0 pypi_0 pypi
[conda] torchaudio 2.6.0 pypi_0 pypi
[conda] torchvision 0.21.0 pypi_0 pypi
[conda] transformers 4.50.0.dev0 pypi_0 pypi
[conda] triton 3.2.0 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.4.dev477+g61c6a5a7
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 NIC10 NIC11 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS 0-12 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS 26-38 2 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS 39-51 3 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS 13-25 1 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS PIX PIX PIX SYS SYS SYS 52-64 4 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX SYS SYS 78-90 6 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX SYS 91-103 7 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX 65-77 5 N/A
NIC0 PIX SYS SYS SYS SYS SYS SYS SYS X PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC1 PIX SYS SYS SYS SYS SYS SYS SYS PIX X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC2 PIX SYS SYS SYS SYS SYS SYS SYS PIX PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC3 SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS SYS
NIC4 SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS
NIC5 SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS
NIC6 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X PIX PIX SYS SYS SYS
NIC7 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX X PIX SYS SYS SYS
NIC8 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX PIX X SYS SYS SYS
NIC9 SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS
NIC10 SYS SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS
NIC11 SYS SYS SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 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
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
π Describe the bug
@WoosukKwon This error is likely a processor-related error.
The error happens for both llm.chat() and llm.generate(). It says Attempted to assign XXX multimodal tokens to YYY placeholders. This error only happens when there are image inputs, but is arbitrary to image (i.e. it remains when replacing images with other images). This error happens only when len(messages)>=32, i.e. if I input messages individually for len(messages) times or using a mini-batched version, it does not raise an error.
Minimum reproduction example:
from vllm import LLM, SamplingParams
import torch
if __name__ == '__main__':
model = LLM(
model="google/gemma-3-27b-it",
max_model_len=8192,
tensor_parallel_size=1,
limit_mm_per_prompt={"image": 5},
tokenizer_mode="auto"
)
sampling_params = SamplingParams(temperature=1,max_tokens=8192,stop_token_ids=None)
messages = torch.load("messages.pt") # contanins 64 messages, the error does not matter whether you input any image or not
response = model.chat(
messages=messages,
sampling_params=sampling_params,
chat_template=None,
)
outputs = []
for out in response:
generated_text = out.outputs[0].text
outputs.append(generated_text)
print(outputs)
Error:
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Processed prompts: 47%|ββββββββββββ | 30/64 [00:10<00:12, 2.77it/s, est. speed input: 4163.14 toks/s, output: 481.12 toks/s]ERROR 03-16 12:28:39 [core.py:340] EngineCore hit an exception: Traceback (most recent call last):
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/engine/core.py", line 333, in run_engine_core
ERROR 03-16 12:28:39 [core.py:340] engine_core.run_busy_loop()
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/engine/core.py", line 367, in run_busy_loop
ERROR 03-16 12:28:39 [core.py:340] outputs = step_fn()
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/engine/core.py", line 192, in step
ERROR 03-16 12:28:39 [core.py:340] output = self.model_executor.execute_model(scheduler_output)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/executor/abstract.py", line 80, in execute_model
ERROR 03-16 12:28:39 [core.py:340] output = self.collective_rpc("execute_model",
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
ERROR 03-16 12:28:39 [core.py:340] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/utils.py", line 2216, in run_method
ERROR 03-16 12:28:39 [core.py:340] return func(*args, **kwargs)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/miniconda3/envs/pae/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
ERROR 03-16 12:28:39 [core.py:340] return func(*args, **kwargs)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/worker/gpu_worker.py", line 242, in execute_model
ERROR 03-16 12:28:39 [core.py:340] output = self.model_runner.execute_model(scheduler_output)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/miniconda3/envs/pae/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
ERROR 03-16 12:28:39 [core.py:340] return func(*args, **kwargs)
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/v1/worker/gpu_model_runner.py", line 961, in execute_model
ERROR 03-16 12:28:39 [core.py:340] inputs_embeds = self.model.get_input_embeddings(
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/model_executor/models/gemma3_mm.py", line 502, in get_input_embeddings
ERROR 03-16 12:28:39 [core.py:340] inputs_embeds = merge_multimodal_embeddings(
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/model_executor/models/utils.py", line 455, in merge_multimodal_embeddings
ERROR 03-16 12:28:39 [core.py:340] return _merge_multimodal_embeddings(
ERROR 03-16 12:28:39 [core.py:340] File "/home/agi/vllm/vllm/model_executor/models/utils.py", line 371, in _merge_multimodal_embeddings
ERROR 03-16 12:28:39 [core.py:340] raise ValueError(
ERROR 03-16 12:28:39 [core.py:340] ValueError: Attempted to assign 256 + 74 = 330 multimodal tokens to 332 placeholders
ERROR 03-16 12:28:39 [core.py:340]
CRITICAL 03-16 12:28:39 [core_client.py:269] Got fatal signal from worker processes, shutting down. See stack trace above for root cause issue.
Killed
Before submitting a new issueβ¦
- 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.
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Reactions: 1
- Comments: 18 (6 by maintainers)
No, that PR only fixes Gemma3
@DarkLight1337 this error only happens to V1