[Bug]:ModuleNotFoundError: No module named 'flash_attn.flash_attn_interface'

[shell-nlp]

Your current environment

The output of python collect_env.py

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 20.04.6 LTS (x86_64)
GCC version                  : (Ubuntu 9.4.0-1ubuntu1~20.04.3) 9.4.0
Clang version                : 10.0.0-4ubuntu1 
CMake version                : Could not collect
Libc version                 : glibc-2.31

==============================
       PyTorch Info
==============================
PyTorch version              : 2.8.0+cu126
Is debug build               : False
CUDA used to build PyTorch   : 12.6
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.11.10 (main, Oct  8 2024, 00:19:50) [Clang 18.1.8 ] (64-bit runtime)
Python platform              : Linux-5.15.0-91-generic-x86_64-with-glibc2.31

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.6.85
CUDA_MODULE_LOADING set to   : LAZY
GPU models and configuration : 
GPU 0: NVIDIA A800 80GB PCIe
GPU 1: NVIDIA A800 80GB PCIe
GPU 2: NVIDIA A800 80GB PCIe
GPU 3: NVIDIA A800 80GB PCIe
GPU 4: NVIDIA A800 80GB PCIe
GPU 5: NVIDIA A800 80GB PCIe
GPU 6: NVIDIA A800 80GB PCIe
GPU 7: NVIDIA A800 80GB PCIe

Nvidia driver version        : 570.158.01
cuDNN version                : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.5.0
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
Byte Order:                         Little Endian
Address sizes:                      52 bits physical, 57 bits virtual
CPU(s):                             64
On-line CPU(s) list:                0-63
Thread(s) per core:                 2
Core(s) per socket:                 16
Socket(s):                          2
NUMA node(s):                       2
Vendor ID:                          GenuineIntel
CPU family:                         6
Model:                              106
Model name:                         Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
Stepping:                           6
CPU MHz:                            900.000
CPU max MHz:                        3400.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4800.00
Virtualization:                     VT-x
L1d cache:                          1.5 MiB
L1i cache:                          1 MiB
L2 cache:                           40 MiB
L3 cache:                           48 MiB
NUMA node0 CPU(s):                  0-15,32-47
NUMA node1 CPU(s):                  16-31,48-63
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
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
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected
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 pni pclmulqdq dtes64 monitor ds_cpl vmx 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 invpcid_single ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.2.10
[pip3] mypy-extensions==1.1.0
[pip3] numpy==1.26.4
[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==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.13.0
[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==0.7.1
[pip3] nvidia-ml-py==12.570.86
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvshmem-cu12==3.3.9
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] onnx==1.17.0
[pip3] onnxruntime==1.19.2
[pip3] pynvml==12.0.0
[pip3] pytorch-wpe==0.0.1
[pip3] pyzmq==26.2.0
[pip3] sentence-transformers==3.2.0
[pip3] torch==2.8.0+cu126
[pip3] torch-complex==0.4.4
[pip3] torch-memory-saver==0.0.8
[pip3] torchao==0.9.0
[pip3] torchaudio==2.8.0
[pip3] torchvision==0.23.0
[pip3] transformers==4.56.1
[pip3] triton==3.4.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.10.2
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV8     PXB     PXB     SYS     SYS     SYS     SYS     0-15,32-47      0               N/A
GPU1    NV8      X      PXB     PXB     SYS     SYS     SYS     SYS     0-15,32-47      0               N/A
GPU2    PXB     PXB      X      NV8     SYS     SYS     SYS     SYS     0-15,32-47      0               N/A
GPU3    PXB     PXB     NV8      X      SYS     SYS     SYS     SYS     0-15,32-47      0               N/A
GPU4    SYS     SYS     SYS     SYS      X      NV4     PXB     PXB     16-31,48-63     1               N/A
GPU5    SYS     SYS     SYS     SYS     NV4      X      PXB     PXB     16-31,48-63     1               N/A
GPU6    SYS     SYS     SYS     SYS     PXB     PXB      X      NV8     16-31,48-63     1               N/A
GPU7    SYS     SYS     SYS     SYS     PXB     PXB     NV8      X      16-31,48-63     1               N/A

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

==============================
     Environment Variables
==============================
NCCL_P2P_DISABLE=1
NCCL_LL_THRESHOLD=0
LD_LIBRARY_PATH=/home/dev/cudnn892/vitstr/lib:/usr/local/cuda-12.6/lib64:/usr/include/nccl.h:/usr/lib/x86_64-linux-gnu
NCCL_IB_DISABLE=1
CUDA_HOME=/usr/local/cuda-12.6
CUDA_HOME=/usr/local/cuda-12.6
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY

🐛 Describe the bug

Unable to start the qwen2.5vl-awq model

if __name__ == "__main__":

    from vllm import LLM, SamplingParams
    import os

    os.environ["CUDA_VISIBLE_DEVICES"] = "3"
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
    ]
    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

    llm = LLM(model="/home/dev/model/Qwen/Qwen2___5-VL-32B-Instruct-AWQ/")

    outputs = llm.generate(prompts, sampling_params)

    # Print the outputs.
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718] EngineCore failed to start.
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718] Traceback (most recent call last):
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 709, in run_engine_core
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 505, in __init__
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     super().__init__(vllm_config, executor_class, log_stats,
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 91, in __init__
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     self._initialize_kv_caches(vllm_config)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 183, in _initialize_kv_caches
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     self.model_executor.determine_available_memory())
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/executor/abstract.py", line 84, in determine_available_memory
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return self.collective_rpc("determine_available_memory")
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     answer = run_method(self.driver_worker, method, args, kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/utils/__init__.py", line 3060, in run_method
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return func(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return func(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/worker/gpu_worker.py", line 263, in determine_available_memory
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     self.model_runner.profile_run()
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/worker/gpu_model_runner.py", line 3017, in profile_run
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     self.model.get_multimodal_embeddings(
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1138, in get_multimodal_embeddings
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     video_embeddings = self._process_video_input(multimodal_input)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1088, in _process_video_input
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     video_embeds = self.visual(pixel_values_videos,
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 811, in forward
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     hidden_states = blk(
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]                     ^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 455, in forward
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     x_attn = self.attn(self.norm1(x),
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]              ^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 398, in forward
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     from xformers import ops as xops
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/__init__.py", line 9, in <module>
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     from .fmha import (
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/fmha/__init__.py", line 10, in <module>
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     from . import attn_bias, ck, ck_splitk, cutlass, flash, flash3, triton_splitk
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/fmha/flash.py", line 68, in <module>
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718]     import flash_attn.flash_attn_interface
(EngineCore_DP0 pid=1531425) ERROR 09-21 22:46:24 [core.py:718] ModuleNotFoundError: No module named 'flash_attn.flash_attn_interface'
(EngineCore_DP0 pid=1531425) Process EngineCore_DP0:
(EngineCore_DP0 pid=1531425) Traceback (most recent call last):
(EngineCore_DP0 pid=1531425)   File "/home/dev/.local/share/uv/python/cpython-3.11.10-linux-x86_64-gnu/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_DP0 pid=1531425)     self.run()
(EngineCore_DP0 pid=1531425)   File "/home/dev/.local/share/uv/python/cpython-3.11.10-linux-x86_64-gnu/lib/python3.11/multiprocessing/process.py", line 108, in run
(EngineCore_DP0 pid=1531425)     self._target(*self._args, **self._kwargs)
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 722, in run_engine_core
(EngineCore_DP0 pid=1531425)     raise e
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 709, in run_engine_core
(EngineCore_DP0 pid=1531425)     engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=1531425)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 505, in __init__
(EngineCore_DP0 pid=1531425)     super().__init__(vllm_config, executor_class, log_stats,
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 91, in __init__
(EngineCore_DP0 pid=1531425)     self._initialize_kv_caches(vllm_config)
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core.py", line 183, in _initialize_kv_caches
(EngineCore_DP0 pid=1531425)     self.model_executor.determine_available_memory())
(EngineCore_DP0 pid=1531425)     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/executor/abstract.py", line 84, in determine_available_memory
(EngineCore_DP0 pid=1531425)     return self.collective_rpc("determine_available_memory")
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
(EngineCore_DP0 pid=1531425)     answer = run_method(self.driver_worker, method, args, kwargs)
(EngineCore_DP0 pid=1531425)              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/utils/__init__.py", line 3060, in run_method
(EngineCore_DP0 pid=1531425)     return func(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
(EngineCore_DP0 pid=1531425)     return func(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/worker/gpu_worker.py", line 263, in determine_available_memory
(EngineCore_DP0 pid=1531425)     self.model_runner.profile_run()
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/worker/gpu_model_runner.py", line 3017, in profile_run
(EngineCore_DP0 pid=1531425)     self.model.get_multimodal_embeddings(
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1138, in get_multimodal_embeddings
(EngineCore_DP0 pid=1531425)     video_embeddings = self._process_video_input(multimodal_input)
(EngineCore_DP0 pid=1531425)                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 1088, in _process_video_input
(EngineCore_DP0 pid=1531425)     video_embeds = self.visual(pixel_values_videos,
(EngineCore_DP0 pid=1531425)                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425)     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425)     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 811, in forward
(EngineCore_DP0 pid=1531425)     hidden_states = blk(
(EngineCore_DP0 pid=1531425)                     ^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425)     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425)     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 455, in forward
(EngineCore_DP0 pid=1531425)     x_attn = self.attn(self.norm1(x),
(EngineCore_DP0 pid=1531425)              ^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
(EngineCore_DP0 pid=1531425)     return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
(EngineCore_DP0 pid=1531425)     return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=1531425)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/model_executor/models/qwen2_5_vl.py", line 398, in forward
(EngineCore_DP0 pid=1531425)     from xformers import ops as xops
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/__init__.py", line 9, in <module>
(EngineCore_DP0 pid=1531425)     from .fmha import (
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/fmha/__init__.py", line 10, in <module>
(EngineCore_DP0 pid=1531425)     from . import attn_bias, ck, ck_splitk, cutlass, flash, flash3, triton_splitk
(EngineCore_DP0 pid=1531425)   File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/xformers/ops/fmha/flash.py", line 68, in <module>
(EngineCore_DP0 pid=1531425)     import flash_attn.flash_attn_interface
(EngineCore_DP0 pid=1531425) ModuleNotFoundError: No module named 'flash_attn.flash_attn_interface'
[rank0]:[W921 22:46:25.124322876 ProcessGroupNCCL.cpp:1538] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
Traceback (most recent call last):
  File "/home/dev/liuyu/project/gpt_server/test_bug.py", line 14, in <module>
    llm = LLM(model="/home/dev/model/Qwen/Qwen2___5-VL-32B-Instruct-AWQ/")
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/entrypoints/llm.py", line 282, in __init__
    self.llm_engine = LLMEngine.from_engine_args(
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/engine/llm_engine.py", line 493, in from_engine_args
    return engine_cls.from_vllm_config(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/llm_engine.py", line 134, in from_vllm_config
    return cls(vllm_config=vllm_config,
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/llm_engine.py", line 111, in __init__
    self.engine_core = EngineCoreClient.make_client(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core_client.py", line 80, in make_client
    return SyncMPClient(vllm_config, executor_class, log_stats)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core_client.py", line 602, in __init__
    super().__init__(
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/core_client.py", line 448, in __init__
    with launch_core_engines(vllm_config, executor_class,
  File "/home/dev/.local/share/uv/python/cpython-3.11.10-linux-x86_64-gnu/lib/python3.11/contextlib.py", line 144, in __exit__
    next(self.gen)
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/utils.py", line 729, in launch_core_engines
    wait_for_engine_startup(
  File "/home/dev/liuyu/project/gpt_server/.venv/lib/python3.11/site-packages/vllm/v1/engine/utils.py", line 782, in wait_for_engine_startup
    raise RuntimeError("Engine core initialization failed. "
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}

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.

[ZJY0516]

Could you please tyr to run this in your environment?

python -c "import flash_attn; import flash_attn.flash_attn_interface; print('success')"

[shell-nlp]

Could you please tyr to run this in your environment?您能尝试在您的环境中运行它吗？

python -c "import flash_attn; import flash_attn.flash_attn_interface; print('success')"

Traceback (most recent call last):
File "", line 1, in
ModuleNotFoundError: No module named 'flash_attn'

In previous versions, the program could run normally even without installing flash_attn. However, starting from version 0.10.2, the program cannot run and a ModuleNotFoundError: No module named 'flash_attn.flash_attn_interface' error occurs.

[ZJY0516]

https://github.com/facebookresearch/xformers/blob/840bcec7feca2244779014cf137946c033d68538/xformers/ops/fmha/flash.py#L66C1-L69C1

elif importlib.util.find_spec("flash_attn"):
    import flash_attn
    import flash_attn.flash_attn_interface

It's strange that the error occurs for flash_attn.flash_attn_interface rather than import flash_attn. Since importlib.util.find_spec("flash_attn") returns True, it indicates that flash_attn is indeed installed in your environment.

The most straightforward solution would likely be to manually install the flash-attn package.

[shell-nlp]

After manually installing the flash-attn package, the issue has been resolved.

[shell-nlp]

@ZJY0516 I did not see any dependency on flash_atten specified in the requirements.

[ZJY0516]

flash-attn is not a strict requirement for vLLM since it supports multiple attention backends. The error you're seeing seems to originate from xformers