What cause the runtime error nvmlDeviceGetNvLinkRemoteDeviceType_

[HanweiLi-cqu]

my code:

from vllm import LLM, SamplingParams
model_path = "/root/models/codellama/CodeLlama-7b-Instruct"
sample_params = SamplingParams(
    stop = ["Question"],
    max_tokens=2048
)
llm = LLM(
    model=model_path,
    dtype="float32",
    trust_remote_code=True,
    gpu_memory_utilization=0.8,
    tensor_parallel_size=4
)

when I set the tensor_parallel_size=8, get the runtime errors:

RuntimeError: r.nvmlDeviceGetNvLinkRemoteDeviceType_ INTERNAL ASSERT FAILED at "../c10/cuda/driver_api.cpp":27, please report a bug to PyTorch. Can't find nvmlDeviceGetNvLinkRemoteDeviceType: /lib/x86_64-linux-gnu/libnvidia-ml.so.1: undefined symbol: nvmlDeviceGetNvLinkRemoteDeviceType

I thought it might be a problem with memory usage, so I tried to use a different combination of parameters, and the result was as follows:

gpu_memory_utilization	tensor_parallel_size	dtype	reuslt
0.9	8	float32	runtime error
0.8	8	float32	runtime error
0.5	8	float32	runtime error
0.4	8	float32	success
0.8	4	float32	success
0.5	4	float32	success
0.8	8	float16	runtime error
0.5	8	float16	runtime error

I'm curious as to why this is the case. I'm a beginner to VLLM, is there any optimization method of VLLM that causes this to happen?

[HanweiLi-cqu]

by the way, my environment as follows:

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 3.30.0
Libc version: glibc-2.35

Python version: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.4.0-80-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: A100-PCIE-40GB
GPU 1: A100-PCIE-40GB
GPU 2: A100-PCIE-40GB
GPU 3: A100-PCIE-40GB
GPU 4: A100-PCIE-40GB
GPU 5: A100-PCIE-40GB
GPU 6: A100-PCIE-40GB
GPU 7: A100-PCIE-40GB

Nvidia driver version: 450.51.05
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.5
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, 48 bits virtual
Byte Order:                      Little Endian
CPU(s):                          80
On-line CPU(s) list:             0-79
Vendor ID:                       GenuineIntel
Model name:                      Intel(R) Xeon(R) Gold 6248 CPU @ 2.50GHz
CPU family:                      6
Model:                           85
Thread(s) per core:              2
Core(s) per socket:              20
Socket(s):                       2
Stepping:                        7
CPU max MHz:                     3900.0000
CPU min MHz:                     1000.0000
BogoMIPS:                        5000.00
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 cdp_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 mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts pku ospke avx512_vnni md_clear flush_l1d arch_capabilities
Virtualization:                  VT-x
L1d cache:                       1.3 MiB (40 instances)
L1i cache:                       1.3 MiB (40 instances)
L2 cache:                        40 MiB (40 instances)
L3 cache:                        55 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
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
Vulnerability Itlb multihit:     KVM: Mitigation: Split huge pages
Vulnerability L1tf:              Not affected
Vulnerability Mds:               Not affected
Vulnerability Meltdown:          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
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; TSX disabled

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.0
[pip3] torchvision==0.18.0
[pip3] transformers==4.42.4
[pip3] triton==2.3.0
[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] torchvision               0.18.0                   pypi_0    pypi
[conda] transformers              4.42.4                   pypi_0    pypi
[conda] triton                    2.3.0                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.1
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     NODE    NODE    SYS     SYS     SYS     SYS     0,2,4,6,8,10    0
GPU1    PIX      X      NODE    NODE    SYS     SYS     SYS     SYS     0,2,4,6,8,10    0
GPU2    NODE    NODE     X      PIX     SYS     SYS     SYS     SYS     0,2,4,6,8,10    0
GPU3    NODE    NODE    PIX      X      SYS     SYS     SYS     SYS     0,2,4,6,8,10    0
GPU4    SYS     SYS     SYS     SYS      X      PIX     NODE    NODE    1,3,5,7,9,11    1
GPU5    SYS     SYS     SYS     SYS     PIX      X      NODE    NODE    1,3,5,7,9,11    1
GPU6    SYS     SYS     SYS     SYS     NODE    NODE     X      PIX     1,3,5,7,9,11    1
GPU7    SYS     SYS     SYS     SYS     NODE    NODE    PIX      X      1,3,5,7,9,11    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

[SefaZeng]

Do you solve this?

[HanweiLi-cqu]

Yes, I adjusted the parameters gpu_memory_utilisation and tensor_parallel_size. The exact parameter information I have given in the table above.