[Bug]: (v0.7.2): RuntimeError: CUDA error: an illegal memory access was encountered #13939
Description
Your current environment
The output of `python collect_env.py`
INFO 02-26 19:10:17 __init__.py:190] Automatically detected platform cuda.
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.31.4
Libc version: glibc-2.35
Python version: 3.12.9 (main, Feb 5 2025, 08:49:00) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.8.0-51-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A30
GPU 1: NVIDIA A30
GPU 2: NVIDIA A30
GPU 3: NVIDIA A30
Nvidia driver version: 550.120
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): 144
On-line CPU(s) list: 0-143
Vendor ID: GenuineIntel
BIOS Vendor ID: Intel
Model name: Intel(R) Xeon(R) Platinum 8452Y
BIOS Model name: Intel(R) Xeon(R) Platinum 8452Y
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 36
Socket(s): 2
Stepping: 8
CPU max MHz: 3200.0000
CPU min MHz: 800.0000
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 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 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi 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 ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 3.4 MiB (72 instances)
L1i cache: 2.3 MiB (72 instances)
L2 cache: 144 MiB (72 instances)
L3 cache: 135 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,130,132,134,136,138,140,142
NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143
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: Not affected
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==1.26.4
[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-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] pyzmq==26.2.1
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.48.2
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE SYS SYS 0,2,4,6,8,10 0 N/A
GPU1 NODE X SYS SYS 0,2,4,6,8,10 0 N/A
GPU2 SYS SYS X NODE 1,3,5,7,9,11 1 N/A
GPU3 SYS SYS NODE X 1,3,5,7,9,11 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
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.1 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
NCCL_VERSION=2.17.1-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_PRODUCT_NAME=CUDA
VLLM_USAGE_SOURCE=production-docker-image
NVIDIA_CUDA_END_OF_LIFE=1
CUDA_VERSION=12.1.0
CUDA_VISIBLE_DEVICES=3
CUDA_VISIBLE_DEVICES=3
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
I updated vllm to version 0.7.2 but still observed this error (already mentioned in #12233 ), but with different error log.
INFO 02-25 11:11:31 metrics.py:455] Avg prompt throughput: 2082.8 tokens/s, Avg generation throughput: 194.4 tokens/s, Running: 3 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 4.8%, CPU KV cache usage: 0.0%.
INFO 02-25 11:11:31 metrics.py:471] Prefix cache hit rate: GPU: 52.36%, CPU: 0.00%
INFO: 172.27.0.4:60994 - "POST /v1/chat/completions HTTP/1.0" 200 OK
INFO: 172.27.0.4:32774 - "POST /v1/chat/completions HTTP/1.0" 200 OK
INFO: 172.27.0.4:32816 - "POST /v1/chat/completions HTTP/1.0" 200 OK
INFO: 172.27.0.4:32790 - "POST /v1/chat/completions HTTP/1.0" 200 OK
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
CRITICAL 02-25 11:11:34 launcher.py:101] MQLLMEngine is already dead, terminating server process
INFO: 172.27.0.4:32796 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
INFO: 172.27.0.4:32810 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
INFO: 172.27.0.4:32818 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
INFO: 172.27.0.4:32822 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
INFO: 172.27.0.4:32830 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
INFO: 172.27.0.4:32792 - "POST /v1/chat/completions HTTP/1.0" 500 Internal Server Error
ERROR 02-25 11:11:34 engine.py:139] RuntimeError('CUDA error: an illegal memory access was encountered\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\n')
ERROR 02-25 11:11:34 engine.py:139] Traceback (most recent call last):
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 137, in start
ERROR 02-25 11:11:34 engine.py:139] self.run_engine_loop()
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 200, in run_engine_loop
ERROR 02-25 11:11:34 engine.py:139] request_outputs = self.engine_step()
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 218, in engine_step
ERROR 02-25 11:11:34 engine.py:139] raise e
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 209, in engine_step
ERROR 02-25 11:11:34 engine.py:139] return self.engine.step()
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py", line 1386, in step
ERROR 02-25 11:11:34 engine.py:139] outputs = self.model_executor.execute_model(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/executor/executor_base.py", line 138, in execute_model
ERROR 02-25 11:11:34 engine.py:139] output = self.collective_rpc("execute_model",
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/executor/uniproc_executor.py", line 51, in collective_rpc
ERROR 02-25 11:11:34 engine.py:139] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/utils.py", line 2220, in run_method
ERROR 02-25 11:11:34 engine.py:139] return func(*args, **kwargs)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/worker/worker_base.py", line 413, in execute_model
ERROR 02-25 11:11:34 engine.py:139] output = self.model_runner.execute_model(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
ERROR 02-25 11:11:34 engine.py:139] return func(*args, **kwargs)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/worker/model_runner.py", line 1775, in execute_model
ERROR 02-25 11:11:34 engine.py:139] output: SamplerOutput = self.model.sample(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2.py", line 505, in sample
ERROR 02-25 11:11:34 engine.py:139] next_tokens = self.sampler(logits, sampling_metadata)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
ERROR 02-25 11:11:34 engine.py:139] return self._call_impl(*args, **kwargs)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
ERROR 02-25 11:11:34 engine.py:139] return forward_call(*args, **kwargs)
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/layers/sampler.py", line 245, in forward
ERROR 02-25 11:11:34 engine.py:139] self._init_sampling_tensors(logits, sampling_metadata)
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/layers/sampler.py", line 209, in _init_sampling_tensors
ERROR 02-25 11:11:34 engine.py:139] do_min_p) = SamplingTensors.from_sampling_metadata(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/sampling_metadata.py", line 480, in from_sampling_metadata
ERROR 02-25 11:11:34 engine.py:139] sampling_tensors = SamplingTensors.from_lists(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/sampling_metadata.py", line 538, in from_lists
ERROR 02-25 11:11:34 engine.py:139] temperatures_t = torch.tensor(
ERROR 02-25 11:11:34 engine.py:139] ^^^^^^^^^^^^^
ERROR 02-25 11:11:34 engine.py:139] RuntimeError: CUDA error: an illegal memory access was encountered
ERROR 02-25 11:11:34 engine.py:139] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
ERROR 02-25 11:11:34 engine.py:139] For debugging consider passing CUDA_LAUNCH_BLOCKING=1
ERROR 02-25 11:11:34 engine.py:139] Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
ERROR 02-25 11:11:34 engine.py:139]
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO: Application shutdown complete.
INFO: Finished server process [1]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.