[Bug]: multi-gpu for baichuan2-13B-Chat benchmark_serving

[shudct]

Your current environment

The output of `python collect_env.py`

Collecting environment information...
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
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 3.29.3
Libc version: glibc-2.35

Python version: 3.9.19 (main, May 6 2024, 19:43:03) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.2.0-36-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 4090
GPU 1: NVIDIA GeForce RTX 4090
GPU 2: NVIDIA GeForce RTX 4090
GPU 3: NVIDIA GeForce RTX 4090
GPU 4: NVIDIA GeForce RTX 4090
GPU 5: NVIDIA GeForce RTX 4090
GPU 6: NVIDIA GeForce RTX 4090
GPU 7: NVIDIA GeForce RTX 4090

Nvidia driver version: 525.147.05
cuDNN version: Probably one of the following:
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn.so.8
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_adv_train.so.8
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8
/usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8
/usr/local/cuda-11.8/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:
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): 128
On-line CPU(s) list: 0-127
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 2
Stepping: 6
CPU max MHz: 3500.0000
CPU min MHz: 800.0000
BogoMIPS: 4600.00
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 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 intel_ppin 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 hwp hwp_act_window hwp_epp hwp_pkg_req 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
Virtualization: VT-x
L1d cache: 3 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 80 MiB (64 instances)
L3 cache: 108 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-31,64-95
NUMA node1 CPU(s): 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 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 IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.0
[pip3] triton==2.3.0
[pip3] vllm_nccl_cu11==2.18.1.0.4.0
[conda] numpy 1.26.4 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.20.5 pypi_0 pypi
[conda] torch 2.3.0 pypi_0 pypi
[conda] triton 2.3.0 pypi_0 pypi
[conda] vllm-nccl-cu11 2.18.1.0.4.0 pypi_0 pypiROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.4.2
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
GPU0 X PIX PIX PIX SYS SYS SYS SYS 0-31,64-95 0
GPU1 PIX X PIX PIX SYS SYS SYS SYS 0-31,64-95 0
GPU2 PIX PIX X PIX SYS SYS SYS SYS 0-31,64-95 0
GPU3 PIX PIX PIX X SYS SYS SYS SYS 0-31,64-95 0
GPU4 SYS SYS SYS SYS X PIX PIX PIX 32-63,96-127 1
GPU5 SYS SYS SYS SYS PIX X PIX PIX 32-63,96-127 1
GPU6 SYS SYS SYS SYS PIX PIX X PIX 32-63,96-127 1
GPU7 SYS SYS SYS SYS PIX PIX PIX X 32-63,96-127 1

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

CUDA_VISIBLE_DEVICES=1,2 python -m vllm.entrypoints.openai.api_server --model /mnt/ddata/models/Baichuan2-13B-Chat --trust-remote-code --port 5000 --tensor-parallel-size 2

Traceback (most recent call last):
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/vllm/entrypoints/openai/api_server.py", line 168, in
engine = AsyncLLMEngine.from_engine_args(
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/vllm/engine/async_llm_engine.py", line 357, in from_engine_args
initialize_ray_cluster(engine_config.parallel_config)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/vllm/executor/ray_utils.py", line 79, in initialize_ray_cluster
ray.init(address=ray_address, ignore_reinit_error=True)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/client_mode_hook.py", line 103, in wrapper
return func(*args, **kwargs)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/worker.py", line 1561, in init
bootstrap_address = services.canonicalize_bootstrap_address(address, _temp_dir)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/services.py", line 541, in canonicalize_bootstrap_address
addr = get_ray_address_from_environment(addr, temp_dir)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/services.py", line 404, in get_ray_address_from_environment
gcs_addrs = find_gcs_addresses()
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/services.py", line 375, in find_gcs_addresses
return _find_address_from_flag("--gcs-address")
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/ray/_private/services.py", line 342, in _find_address_from_flag
proc = psutil.Process(pid)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/init.py", line 323, in init
self._init(pid)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/init.py", line 359, in _init
self.create_time()
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/init.py", line 752, in create_time
self._create_time = self._proc.create_time()
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_pslinux.py", line 1714, in wrapper
return fun(self, *args, **kwargs)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_pslinux.py", line 1945, in create_time
ctime = float(self._parse_stat_file()['create_time'])
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_pslinux.py", line 1714, in wrapper
return fun(self, *args, **kwargs)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_common.py", line 497, in wrapper
raise raise_from(err, None)
File "", line 3, in raise_from
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_common.py", line 495, in wrapper
return fun(self)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_pslinux.py", line 1777, in _parse_stat_file
data = bcat("%s/%s/stat" % (self._procfs_path, self.pid))
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_common.py", line 840, in bcat
return cat(fname, fallback=fallback, _open=open_binary)
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_common.py", line 828, in cat
with _open(fname) as f:
File "/usr/local/anaconda3/envs/vllm/lib/python3.9/site-packages/psutil/_common.py", line 788, in open_binary
return open(fname, "rb", buffering=FILE_READ_BUFFER_SIZE)
FileNotFoundError: [Errno 2] No such file or directory: '/proc/5032/stat'

In fact, no 5032 in process.

how can i run benchmark with 2 gpu ?