vllm-project
[Bug]: ERROR 07-26 14:50:35 multiproc_worker_utils.py:120] Worker VllmWorkerProcess pid 214281 died, exit code: -11
Your current environment
PyTorch version: 2.3.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
CMake version: version 3.30.1
Libc version: glibc-2.31
Python version: 3.9.19 (main, May 6 2024, 19:43:03) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.4.0-190-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.2.91
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: 550.54.15
cuDNN version: Probably one of the following:
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_adv_train.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8
/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_ops_train.so.8
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
架构： x86_64
CPU 运行模式： 32-bit, 64-bit
字节序： Little Endian
Address sizes: 46 bits physical, 57 bits virtual
CPU: 128
在线 CPU 列表： 0-127
每个核的线程数： 2
每个座的核数： 32
座： 2
NUMA 节点： 2
厂商 ID： GenuineIntel
CPU 系列： 6
型号： 106
型号名称： Intel(R) Xeon(R) Platinum 8358P CPU @ 2.60GHz
步进： 6
Frequency boost: enabled
CPU MHz： 882.709
CPU 最大 MHz： 2601.0000
CPU 最小 MHz： 800.0000
BogoMIPS： 5200.00
虚拟化： VT-x
L1d 缓存： 3 MiB
L1i 缓存： 2 MiB
L2 缓存： 80 MiB
L3 缓存： 96 MiB
NUMA 节点0 CPU： 0-31,64-95
NUMA 节点1 CPU： 32-63,96-127
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 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Vulnerable, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
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 pni pclmulqdq dtes64 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid md_clear pconfig flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.1
[pip3] torchvision==0.18.1
[pip3] transformers==4.43.2
[pip3] triton==2.3.1
[conda] numpy 1.26.4 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.20.5 pypi_0 pypi
[conda] torch 2.3.1 pypi_0 pypi
[conda] torchvision 0.18.1 pypi_0 pypi
[conda] transformers 4.43.2 pypi_0 pypi
[conda] triton 2.3.1 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.3.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PIX PXB PXB SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU1 PIX X PXB PXB SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU2 PXB PXB X PXB SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU3 PXB PXB PXB X SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU4 SYS SYS SYS SYS X PIX PXB PXB 32-63,96-127 1 N/A
GPU5 SYS SYS SYS SYS PIX X PXB PXB 32-63,96-127 1 N/A
GPU6 SYS SYS SYS SYS PXB PXB X PXB 32-63,96-127 1 N/A
GPU7 SYS SYS SYS SYS PXB PXB PXB X 32-63,96-127 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
🐛 Describe the bug
When I use Nsight system to record the profile which program runs in multi-GPU, the error occurred.
Take a look at examples/offline_inference.py, when I use the QWen/QWen-72B LLM, while configure is
llm = LLM(
model="QWen/QWen-72B",
trust_remote_code=True,
tensor_parallel_size=4,
gpu_memory_utilization=1
)
And the running command is nsys profile python offline_inference.py, the error occurred. I'm sure the the script has no bug becauce, when running python offline_inference.py, there is no bug.
Furthermore, I think that there may be some bugs in multi-GPU environment, so I changed the configure of LLM
llm = LLM(
model="QWen/QWen2-7B-intruct"
)
and run the script with nsys profile python offline_inference.py. There is no bug.
same. cannot do on 2 gpus.
ps: actually it can be run on 2 gpus. but when i run nsys profile along with it, the bug occured. i suspect it is something todo with ram.
Any update on this? I tried with NVIDIA Nsight Systems version 2023.4.1.97-234133557503v0, but even with that, it is not working.
Any update on this? I tried with
NVIDIA Nsight Systems version 2023.4.1.97-234133557503v0, but even with that, it is not working.
same... i guess u may try with smaller model
same issue. My nsys version NVIDIA Nsight Systems version 2024.5.1.113-245134619542v0 and vllm0.5.4@e6e42e
same issue. ERROR 08-15 19:14:30 multiproc_worker_utils.py:120] Worker VllmWorkerProcess pid 65117 died, exit code: -11
@vlllm devs,
Just checking in on this issue since a few of us are experiencing it. If there’s anything we can do to help move it forward, please let us know. Thanks for all your hard work!
Apologies I had made some progress on this will get back to it today/tomorrow.
家人们，我成功了！启动的时候设置下两个参数，参考如下：
llm = LLM(model=model_path, tokenizer=model_path, max_num_batched_tokens=32768, max_model_len=32768, tensor_parallel_size=8, trust_remote_code=True, load_format = "auto", enforce_eager=True, \ ray_workers_use_nsight=True, distributed_executor_backend="ray" )
关键参数： ray_workers_use_nsight=True, distributed_executor_backend="ray"
使用的 nsys 版本如下： https://developer.nvidia.com/downloads/assets/tools/secure/nsight-systems/2024_4/NsightSystems-linux-cli-public-2024.4.1.61-3431596.deb
vllm==0.5.4
家人们，我成功了！启动的时候设置下两个参数，参考如下：
llm = LLM(model=model_path, tokenizer=model_path, max_num_batched_tokens=32768, max_model_len=32768, tensor_parallel_size=8, trust_remote_code=True, load_format = "auto", enforce_eager=True, \ ray_workers_use_nsight=True, distributed_executor_backend="ray" )关键参数：
ray_workers_use_nsight=True, distributed_executor_backend="ray"使用的 nsys 版本如下： https://developer.nvidia.com/downloads/assets/tools/secure/nsight-systems/2024_4/NsightSystems-linux-cli-public-2024.4.1.61-3431596.deb
vllm==0.5.4
感谢您的提醒！但是后面执行benchmark_serving的时候出现了段错误，您有遇到吗？
This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
I ran into the same issue on vllm-0.6.4. Any progress on that? init LLM with LLM( ray_workers_use_nsight=True, distributed_executor_backend="ray" )，as described above.
This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!
This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!