[Bug]: Hangs on mulit-node setup when len(prompt) > max_model_len

Your current environment

Collecting environment information...
/traindata/eugen/lotus/.venv/lib/python3.12/site-packages/torch/cuda/__init__.py:789: UserWarning: Can't initialize NVML
  warnings.warn("Can't initialize NVML")
/traindata/eugen/lotus/.venv/lib/python3.12/site-packages/torch/cuda/__init__.py:789: UserWarning: Can't initialize NVML
  warnings.warn("Can't initialize NVML")
==============================
        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 4.0.2
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.7.1+cu126
Is debug build               : False
CUDA used to build PyTorch   : 12.6
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.9 | packaged by Anaconda, Inc. | (main, Feb  6 2025, 18:56:27) [GCC 11.2.0] (64-bit runtime)
Python platform              : Linux-6.8.0-1029-aws-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : 12.8.93
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : Could not collect
Nvidia driver version        : Could not collect
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:                        46 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               48
On-line CPU(s) list:                  0-47
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
CPU family:                           6
Model:                                85
Thread(s) per core:                   1
Core(s) per socket:                   24
Socket(s):                            2
Stepping:                             7
BogoMIPS:                             4999.98
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch pti fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves ida arat pku ospke
Hypervisor vendor:                    KVM
Virtualization type:                  full
L1d cache:                            1.5 MiB (48 instances)
L1i cache:                            1.5 MiB (48 instances)
L2 cache:                             48 MiB (48 instances)
L3 cache:                             71.5 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-23
NUMA node1 CPU(s):                    24-47
Vulnerability Gather data sampling:   Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit:          KVM: Mitigation: VMX unsupported
Vulnerability L1tf:                   Mitigation; PTE Inversion
Vulnerability Mds:                    Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Meltdown:               Mitigation; PTI
Vulnerability Mmio stale data:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Vulnerable
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Vulnerable
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Retpoline
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

==============================
Versions of relevant libraries
==============================
[pip3] mypy_extensions==1.1.0
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] pyzmq==27.0.1
[pip3] torch==2.7.1
[pip3] torchao==0.12.0
[pip3] torchaudio==2.7.1
[pip3] torchvision==0.22.1
[pip3] transformers==4.55.0
[pip3] triton==3.3.1
[conda] No relevant packages

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.10.1.dev504+g0c5254b82 (git sha: 0c5254b82)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/amazon/ofi-nccl/lib:/usr/local/cuda-12.8/lib:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8:/usr/local/cuda-12.8/targets/x86_64-linux/lib/:/usr/local/cuda-12.8/extras/CUPTI/lib64:/usr/local/lib:/usr/lib:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/amazon/ofi-nccl/lib:/usr/local/cuda-12.8/lib:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8:/usr/local/cuda-12.8/targets/x86_64-linux/lib/:/usr/local/cuda-12.8/extras/CUPTI/lib64:/usr/local/lib:/usr/lib:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/amazon/ofi-nccl/lib:/usr/local/cuda-12.8/lib:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8:/usr/local/cuda-12.8/targets/x86_64-linux/lib/:/usr/local/cuda-12.8/extras/CUPTI/lib64:/usr/local/lib:/usr/lib:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/amazon/ofi-nccl/lib:/usr/local/cuda-12.8/lib:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8:/usr/local/cuda-12.8/targets/x86_64-linux/lib/:/usr/local/cuda-12.8/extras/CUPTI/lib64:/usr/local/lib:/usr/lib:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/amazon/ofi-nccl/lib:/usr/local/cuda-12.8/lib:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8:/usr/local/cuda-12.8/targets/x86_64-linux/lib/:/usr/local/cuda-12.8/extras/CUPTI/lib64:/usr/local/lib:/usr/lib
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

🐛 Describe the bug

When running on a single node, an assertion gets raised and propagated correctly:

AssertionError: Sampled token IDs exceed the max model length. Total number of tokens: 10001 > max_model_len: 10000

However, on multi-node vLLM just hangs until it eventually times out and gets killed. I'm assuming one of the ranks crashes with the same assertion but the error does not get propagated correctly, causing the other ranks to hang.

This is using the LLM python api instead of vllm serve running with tp=8.

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.