[Bug]:RuntimeError: CUDA error: no kernel image is available for execution on the device

[anyiz]

Your current environment

The output of python collect_env.py

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.2 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version                : Could not collect
CMake version                : version 3.28.3
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.7.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
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-6.11.0-26-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.8.93
CUDA_MODULE_LOADING set to   : LAZY
GPU models and configuration : GPU 0: NVIDIA GeForce RTX 5090 D
Nvidia driver version        : 570.133.07
cuDNN version                : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
架构：                                x86_64
CPU 运行模式：                        32-bit, 64-bit
Address sizes:                        46 bits physical, 48 bits virtual
字节序：                              Little Endian
CPU:                                  32
在线 CPU 列表：                       0-31
厂商 ID：                             GenuineIntel
型号名称：                            Intel(R) Core(TM) i9-14900K
CPU 系列：                            6
型号：                                183
每个核的线程数：                      2
每个座的核数：                        24
座：                                  1
步进：                                1
CPU(s) scaling MHz:                   17%
CPU 最大 MHz：                        6000.0000
CPU 最小 MHz：                        800.0000
BogoMIPS：                            6374.40
标记：                                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 vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize pconfig arch_lbr ibt flush_l1d arch_capabilities
虚拟化：                              VT-x
L1d 缓存：                            896 KiB (24 instances)
L1i 缓存：                            1.3 MiB (24 instances)
L2 缓存：                             32 MiB (12 instances)
L3 缓存：                             36 MiB (1 instance)
NUMA 节点：                           1
NUMA 节点0 CPU：                      0-31
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 Reg file data sampling: Mitigation; Clear Register File
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; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic 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] numpy==1.26.0
[pip3] nvidia-cublas-cu12==12.8.3.14
[pip3] nvidia-cuda-cupti-cu12==12.8.57
[pip3] nvidia-cuda-nvrtc-cu12==12.8.61
[pip3] nvidia-cuda-runtime-cu12==12.8.57
[pip3] nvidia-cudnn-cu12==9.7.1.26
[pip3] nvidia-cufft-cu12==11.3.3.41
[pip3] nvidia-cufile-cu12==1.13.0.11
[pip3] nvidia-curand-cu12==10.3.9.55
[pip3] nvidia-cusolver-cu12==11.7.2.55
[pip3] nvidia-cusparse-cu12==12.5.7.53
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.8.61
[pip3] nvidia-nvtx-cu12==12.8.55
[pip3] onnx==1.18.0
[pip3] onnxruntime-gpu==1.21.0
[pip3] pyzmq==26.4.0
[pip3] torch==2.7.0+cu128
[pip3] torchaudio==2.7.0+cu128
[pip3] torchvision==0.22.0+cu128
[pip3] transformers==4.52.4
[pip3] triton==3.3.0
[conda] numpy                     1.26.0                   pypi_0    pypi
[conda] nvidia-cublas-cu12        12.8.3.14                pypi_0    pypi
[conda] nvidia-cuda-cupti-cu12    12.8.57                  pypi_0    pypi
[conda] nvidia-cuda-nvrtc-cu12    12.8.61                  pypi_0    pypi
[conda] nvidia-cuda-runtime-cu12  12.8.57                  pypi_0    pypi
[conda] nvidia-cudnn-cu12         9.7.1.26                 pypi_0    pypi
[conda] nvidia-cufft-cu12         11.3.3.41                pypi_0    pypi
[conda] nvidia-cufile-cu12        1.13.0.11                pypi_0    pypi
[conda] nvidia-curand-cu12        10.3.9.55                pypi_0    pypi
[conda] nvidia-cusolver-cu12      11.7.2.55                pypi_0    pypi
[conda] nvidia-cusparse-cu12      12.5.7.53                pypi_0    pypi
[conda] nvidia-cusparselt-cu12    0.6.3                    pypi_0    pypi
[conda] nvidia-nccl-cu12          2.26.2                   pypi_0    pypi
[conda] nvidia-nvjitlink-cu12     12.8.61                  pypi_0    pypi
[conda] nvidia-nvtx-cu12          12.8.55                  pypi_0    pypi
[conda] pyzmq                     26.4.0                   pypi_0    pypi
[conda] torch                     2.7.0+cu128              pypi_0    pypi
[conda] torchaudio                2.7.0+cu128              pypi_0    pypi
[conda] torchvision               0.22.0+cu128             pypi_0    pypi
[conda] transformers              4.52.4                   pypi_0    pypi
[conda] triton                    3.3.0                    pypi_0    pypi

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
Neuron SDK Version           : N/A
vLLM Version                 : 0.9.0.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
        GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      0-31    0               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
==============================
LD_LIBRARY_PATH=/usr/local/cuda/lib64:
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY

🐛 Describe the bug

When I run this code, my machine reports an errorexamples/offline_inference/prompt_embed_inference.py

error:

INFO 06-02 16:56:19 [__init__.py:243] Automatically detected platform cuda.
Loading checkpoint shards: 100%|██████████████████| 4/4 [00:02<00:00,  1.34it/s]
INFO 06-02 16:56:23 [__init__.py:31] Available plugins for group vllm.general_plugins:
INFO 06-02 16:56:23 [__init__.py:33] - lora_filesystem_resolver -> vllm.plugins.lora_resolvers.filesystem_resolver:register_filesystem_resolver
INFO 06-02 16:56:23 [__init__.py:36] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.
INFO 06-02 16:56:28 [config.py:793] This model supports multiple tasks: {'generate', 'reward', 'classify', 'embed', 'score'}. Defaulting to 'generate'.
WARNING 06-02 16:56:28 [arg_utils.py:1583] --enable-prompt-embeds is not supported by the V1 Engine. Falling back to V0. 
WARNING 06-02 16:56:28 [arg_utils.py:1420] Chunked prefill is enabled by default for models with max_model_len > 32K. Chunked prefill might not work with some features or models. If you encounter any issues, please disable by launching with --enable-chunked-prefill=False.
INFO 06-02 16:56:28 [config.py:2118] Chunked prefill is enabled with max_num_batched_tokens=2048.
INFO 06-02 16:56:28 [llm_engine.py:230] Initializing a V0 LLM engine (v0.9.0.1) with config: model='Meta-Llama-3.1-8B', speculative_config=None, tokenizer='Meta-Llama-3.1-8B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto,  device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=Meta-Llama-3.1-8B, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=None, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"compile_sizes": [], "inductor_compile_config": {"enable_auto_functionalized_v2": false}, "cudagraph_capture_sizes": [256, 248, 240, 232, 224, 216, 208, 200, 192, 184, 176, 168, 160, 152, 144, 136, 128, 120, 112, 104, 96, 88, 80, 72, 64, 56, 48, 40, 32, 24, 16, 8, 4, 2, 1], "max_capture_size": 256}, use_cached_outputs=False, 
INFO 06-02 16:56:28 [cuda.py:292] Using Flash Attention backend.
INFO 06-02 16:56:29 [parallel_state.py:1064] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0
INFO 06-02 16:56:29 [model_runner.py:1170] Starting to load model Meta-Llama-3.1-8B...
Loading safetensors checkpoint shards:   0% Completed | 0/4 [00:00<?, ?it/s]
Loading safetensors checkpoint shards:  25% Completed | 1/4 [00:00<00:01,  2.36it/s]
Loading safetensors checkpoint shards:  50% Completed | 2/4 [00:02<00:02,  1.30s/it]
Loading safetensors checkpoint shards:  75% Completed | 3/4 [00:02<00:00,  1.09it/s]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:03<00:00,  1.13it/s]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:03<00:00,  1.10it/s]

INFO 06-02 16:56:32 [default_loader.py:280] Loading weights took 3.68 seconds
INFO 06-02 16:56:32 [model_runner.py:1202] Model loading took 14.9889 GiB and 3.794536 seconds
[rank0]: Traceback (most recent call last):
[rank0]:   File "/home/ubuntu/wang/6666/vlll11.py", line 96, in <module>
[rank0]:     main()
[rank0]:   File "/home/ubuntu/wang/6666/vlll11.py", line 90, in main
[rank0]:     tokenizer, embedding_layer, llm = init_tokenizer_and_llm(model_name)
[rank0]:                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/wang/6666/vlll11.py", line 30, in init_tokenizer_and_llm
[rank0]:     llm = LLM(model=model_name, enable_prompt_embeds=True)
[rank0]:           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/utils.py", line 1183, in inner
[rank0]:     return fn(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/entrypoints/llm.py", line 253, in __init__
[rank0]:     self.llm_engine = LLMEngine.from_engine_args(
[rank0]:                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 501, in from_engine_args
[rank0]:     return engine_cls.from_vllm_config(
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 477, in from_vllm_config
[rank0]:     return cls(
[rank0]:            ^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 268, in __init__
[rank0]:     self._initialize_kv_caches()
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 413, in _initialize_kv_caches
[rank0]:     self.model_executor.determine_num_available_blocks())
[rank0]:     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 103, in determine_num_available_blocks
[rank0]:     results = self.collective_rpc("determine_num_available_blocks")
[rank0]:               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
[rank0]:     answer = run_method(self.driver_worker, method, args, kwargs)
[rank0]:              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/utils.py", line 2605, in run_method
[rank0]:     return func(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/worker/worker.py", line 253, in determine_num_available_blocks
[rank0]:     self.model_runner.profile_run()
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1299, in profile_run
[rank0]:     self._dummy_run(max_num_batched_tokens, max_num_seqs)
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1425, in _dummy_run
[rank0]:     self.execute_model(model_input, kv_caches, intermediate_tensors)
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1843, in execute_model
[rank0]:     hidden_or_intermediate_states = model_executable(
[rank0]:                                     ^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 580, in forward
[rank0]:     model_output = self.model(input_ids, positions, intermediate_tensors,
[rank0]:                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 172, in __call__
[rank0]:     return self.forward(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 391, in forward
[rank0]:     hidden_states, residual = layer(positions, hidden_states, residual)
[rank0]:                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 304, in forward
[rank0]:     hidden_states = self.self_attn(positions=positions,
[rank0]:                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 199, in forward
[rank0]:     qkv, _ = self.qkv_proj(hidden_states)
[rank0]:              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
[rank0]:     return self._call_impl(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
[rank0]:     return forward_call(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/layers/linear.py", line 486, in forward
[rank0]:     output_parallel = self.quant_method.apply(self, input_, bias)
[rank0]:                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "/home/ubuntu/anaconda3/envs/P3.12/lib/python3.12/site-packages/vllm/model_executor/layers/linear.py", line 202, in apply
[rank0]:     return dispatch_unquantized_gemm()(x, layer.weight, bias)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: RuntimeError: CUDA error: no kernel image is available for execution on the device
[rank0]: CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
[rank0]: For debugging consider passing CUDA_LAUNCH_BLOCKING=1
[rank0]: Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

[rank0]:[W602 16:56:34.312636184 ProcessGroupNCCL.cpp:1476] 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())
(P3.12) ubuntu@ubuntu-MS-7E06:~/wang/6666$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Fri_Feb_21_20:23:50_PST_2025
Cuda compilation tools, release 12.8, V12.8.93
Build cuda_12.8.r12.8/compiler.35583870_0

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.

[anyiz]

I just rebuilt the vllm library from the source code and the result is still the same as above

[helunwencser]

Run into this problem as well.

[v-lmn]

same problem on A800,how to solve

[Leon-Sander]

Same error with rtx 5090 using the docker image

[ypeng1]

Was able to reproduce the issue with meta-llama/Llama-4-Scout-17B-16E-Instruct on docker image 0.9.0.1. The issue does not exist on 0.9.0.

[benjamin-marie]

For me, it works after running all these steps:
git clone https://github.com/vllm-project/vllm.git
cd vllm
python use_existing_torch.py
pip install -r requirements/build.txt
pip install setuptools_scm
mkdir ./tmp
MAX_JOBS=10 CCACHE_DIR=./tmp python setup.py develop

Tested with RunPod RTX 6000 Pro and PyTorch current nightly

[jinlll123]

Same error on 5060ti

1. My cuda version I use is 12.8, and cuDNN and torch are the corresponding versions

2. And I use pip install vllm --extra-index-url https://download.pytorch.org/whl/cu128 to install vllm

3. The command I used to run llm serve is:
   vllm serve Qwen/Qwen2.5-0.5B-Instruct \ --dtype float16 \ --max-model-len 512 \ --max-num-seqs 4 \ --gpu-memory-utilization 0.6

4. This happened when I used the command to send a request
   curl http://localhost:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "Qwen/Qwen2.5-0.5B-Instruct", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Who won the world series in 2020?"} ] }'

5. The error stack is as follows.
   INFO: 127.0.0.1:46401 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error Traceback (most recent call last): File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 504, in run_engine_core raise e File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 493, in run_engine_core engine_core.run_busy_loop() File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 520, in run_busy_loop self._process_engine_step() File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 545, in _process_engine_step outputs = self.step_fn() ^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 226, in step model_output = self.execute_model(scheduler_output) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 213, in execute_model raise err File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 207, in execute_model return self.model_executor.execute_model(scheduler_output) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 86, in execute_model output = self.collective_rpc("execute_model", ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc answer = run_method(self.driver_worker, method, args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/utils.py", line 2605, in run_method return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/worker/gpu_worker.py", line 276, in execute_model output = self.model_runner.execute_model(scheduler_output, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 1196, in execute_model model_output = self.model( ^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 481, in forward hidden_states = self.model(input_ids, positions, intermediate_tensors, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 245, in __call__ model_output = self.forward(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/model_executor/models/qwen2.py", line 340, in forward def forward( File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 838, in _fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 830, in call_wrapped return self._wrapped_call(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 406, in __call__ raise e File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 393, in __call__ return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "<eval_with_key>.50", line 184, in forward submod_1 = self.submod_1(getitem, s0, getitem_1, getitem_2, getitem_3); getitem = getitem_1 = getitem_2 = submod_1 = None ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 830, in call_wrapped return self._wrapped_call(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 406, in __call__ raise e File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/fx/graph_module.py", line 393, in __call__ return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "<eval_with_key>.2", line 5, in forward unified_attention_with_output = torch.ops.vllm.unified_attention_with_output(query_2, key_2, value, output_1, 'model.layers.0.self_attn.attn'); query_2 = key_2 = value = output_1 = unified_attention_with_output = None ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/_ops.py", line 1158, in __call__ return self._op(*args, **(kwargs or {})) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/attention/layer.py", line 425, in unified_attention_with_output self.impl.forward(self, File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/attention/backends/flash_attn.py", line 622, in forward flash_attn_varlen_func( File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/vllm_flash_attn/flash_attn_interface.py", line 227, in flash_attn_varlen_func out, softmax_lse = torch.ops._vllm_fa2_C.varlen_fwd( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/torch/_ops.py", line 1158, in __call__ return self._op(*args, **(kwargs or {})) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA` to enable device-side assertions.

INFO: Shutting down
INFO: Waiting for application shutdown.
INFO: Application shutdown complete.
INFO: Finished server process [38017]`

[allenli178]

same for me

• cuda toolkit 12.8
• gpu driver 570.144
• torch 2.7.0 cu128
• rtx 5090D

[l137295]

5. 127.0.0.1:46401 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error Traceback (most recent call last): File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jin/anaconda3/envs/vllm-py312/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 504, in run_engine_core raise e File "/home/jin/anaconda3/env

I have the same problem, have you solved it? friend

[polarathene]

This PR will be addressing it AFAIK: #19794

[gameboy777x]

Has anyone solved this issue? :)
I encountered a similar problem during serve Qwen2.5-VL using a 5090

error:
RuntimeError: CUDA error: no kernel image is available for execution on the device

my envs:
vllm = 0.9.1
torch = 2.7.0
transformers = 4.52.0
xformers = 0.0.30