vllm: [Bug]: Unable to load Llama-3.1-70B-Instruct using either `vllm serve` or `vllm-openai` docker
Your current environment
The output of `python collect_env.py`
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 24.04 LTS (x86_64)
GCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.39
Python version: 3.10.15 (main, Nov 8 2024, 11:29:01) [GCC 13.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-1018-aws-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.0.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A10G
GPU 1: NVIDIA A10G
GPU 2: NVIDIA A10G
GPU 3: NVIDIA A10G
Nvidia driver version: 555.42.06
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: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 48
On-line CPU(s) list: 0-47
Vendor ID: AuthenticAMD
Model name: AMD EPYC 7R32
CPU family: 23
Model: 49
Thread(s) per core: 2
Core(s) per socket: 24
Socket(s): 1
Stepping: 0
BogoMIPS: 5599.99
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save rdpid
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 768 KiB (24 instances)
L1i cache: 768 KiB (24 instances)
L2 cache: 12 MiB (24 instances)
L3 cache: 96 MiB (6 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-47
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: Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode
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; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.77
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.46.2
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.post1
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 PHB PHB PHB 0-47 0 N/A
GPU1 PHB X PHB PHB 0-47 0 N/A
GPU2 PHB PHB X PHB 0-47 0 N/A
GPU3 PHB PHB PHB X 0-47 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
LD_LIBRARY_PATH=/home/ubuntu/work/llm_dist/.venv/lib/python3.10/site-packages/cv2/../../lib64:
CUDA_MODULE_LOADING=LAZY
Model Input Dumps
No response
🐛 Describe the bug
Tried to run model using vllm pip package:
version: 0.6.3.post1
Command that I ran:
vllm serve $model --host 0.0.0.0 --port 8010 --dtype bfloat16 --enforce-eager --gpu-memory-utilization 0.95 --api-key RnD12345 --max-model-len 4098 --tensor-parallel-size 4 --quantization bitsandbytes --load-format bitsandbytes
Tried using docker image as well:
docker image inspect output:
[
{
"Id": "sha256:9de570dfcdfca4effabe006779215326faf1f812c1d522652c5010801b8e6d78",
"RepoTags": [
"vllm/vllm-openai:latest"
],
"RepoDigests": [
"vllm/vllm-openai@sha256:facbbd4a92c1754675b239a5f22a281ed3aa8bde64662db8919d85d670673aa7"
],
"Parent": "",
"Comment": "buildkit.dockerfile.v0",
"Created": "2024-10-17T10:54:46.210678506-07:00",
"DockerVersion": "",
"Author": "",
"Config": {
"Hostname": "",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"NVARCH=x86_64",
"NVIDIA_REQUIRE_CUDA=cuda>=12.4 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 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536",
"NV_CUDA_CUDART_VERSION=12.4.127-1",
"NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4",
"CUDA_VERSION=12.4.1",
"LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
"NVIDIA_VISIBLE_DEVICES=all",
"NVIDIA_DRIVER_CAPABILITIES=compute,utility",
"DEBIAN_FRONTEND=noninteractive",
"VLLM_USAGE_SOURCE=production-docker-image"
],
"Cmd": null,
"Image": "",
"Volumes": null,
"WorkingDir": "/vllm-workspace",
"Entrypoint": [
"python3",
"-m",
"vllm.entrypoints.openai.api_server"
],
"OnBuild": null,
"Labels": {
"maintainer": "NVIDIA CORPORATION <cudatools@nvidia.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04"
}
},
"Architecture": "amd64",
"Os": "linux",
"Size": 10433172732,
"GraphDriver": {
"Data": {
"LowerDir": "/var/lib/docker/overlay2/6434a00d5febd5b0e5c5f649ba730d6eecb98569a1ca91d070b6d91e76413c74/diff:/var/lib/docker/overlay2/dd0e5c6c529ddf94791c0f64d2ad36ec5d38cfc0a20062e11b12bd532d7c8d1c/diff:/var/lib/docker/overlay2/59dc2d24ef6995a6d7cd14e5d48cd0f8794e011f90ad682edbd71e7167a7ef96/diff:/var/lib/docker/overlay2/4d3d040ed53719f59f0c9dd300e4e05cc7f71dc19fb62468b5838174533909d0/diff:/var/lib/docker/overlay2/fc4f6caf8e0c462529b2209e60fac58cc1bbaa56a5dec19411f21d6b611fed10/diff:/var/lib/docker/overlay2/62d1f4e9911d8387c12c7386bb89aa91d689e5a5e7a50af3a1ae1a3ead2aac22/diff:/var/lib/docker/overlay2/0ea99b169b186ada6653ac6dda2617f17fa3da9112e6ee339937fff09ca69751/diff:/var/lib/docker/overlay2/8821136cefb26d4a59cc1bc75b3c7c57d2c65d5415e6f9e52994098a92969757/diff:/var/lib/docker/overlay2/3b814768ba4a7e39ee721e9c8365a82843ae46575a18d7ee6ce416d7f6c27784/diff:/var/lib/docker/overlay2/577f5d8f7131ef41ab3edc0d0be71053be04108b59ddcde1d768801bc928d3f0/diff:/var/lib/docker/overlay2/70edcf83f3b2e679e35246cc963136beddb591a7fecf966a8ff386aca74baf78/diff:/var/lib/docker/overlay2/3d8c594fc1d94e07c114d452c861daf69920d0f6c03c0988fb4c20254811ff27/diff",
"MergedDir": "/var/lib/docker/overlay2/cd24f65cdf9dad054219845152d5e2490a94ca494c3f65abace5358179f813f1/merged",
"UpperDir": "/var/lib/docker/overlay2/cd24f65cdf9dad054219845152d5e2490a94ca494c3f65abace5358179f813f1/diff",
"WorkDir": "/var/lib/docker/overlay2/cd24f65cdf9dad054219845152d5e2490a94ca494c3f65abace5358179f813f1/work"
},
"Name": "overlay2"
},
"RootFS": {
"Type": "layers",
"Layers": [
"sha256:e0a9f5911802534ba097660206feabeb0247a81e409029167b30e2e1f2803b57",
"sha256:47654eeadbc543f1dd44ebb41c6ca0954b9f1813efabdcd46b0e7f17ac4e9fd1",
"sha256:efe2b79b53de08e199a2ce107d83adc0cbdff94f605e03f5ef51f3df3ae31cfd",
"sha256:46d54736d31f4bfeb749544e22e8611dba11128bdb2cebb820a3b452b50e7d52",
"sha256:809d3bb9c80fb3d31d4c061ba0b38ba4e83b6329e33c2cb2bbf27251a8e527c6",
"sha256:c1773f613c662964cd11fa206779f38c92fb00e3a835e7931070285cfd68aadd",
"sha256:e37cbea0d17fcd8906d4136f2eab993b6eef803eb8141933f596e7b6d78c6636",
"sha256:e819f72bf6d3ec7ed9a85b73f5b1af866fe7765b1d0a7a9908cbca1fde836038",
"sha256:0f1574f66fa6175a23113c89ce6fb60f321c30c428ccccf2f4061c42375fa766",
"sha256:387174fca07f20756620f4cac2d43d9bfd5eb1fb2fba3d3196e37d8302251d38",
"sha256:ff45bc8aa7f980af223369d59806c1a27fd6032bd82734be46f860ad2e7f8325",
"sha256:1ad2df56152854745a66ec7b3fb7547ab6f07013d11ec2d91da353cbddd3d8d0",
"sha256:5749f2a270664189ce6f8f41e9909053b6f3fcf8e7c4a9ac156c68a188d69b02"
]
},
"Metadata": {
"LastTagTime": "0001-01-01T00:00:00Z"
}
}
]
docker cmd used:
docker run --name llm_dist --gpus all \
-v $volume:/data \
-p 8010:80 \
--ipc=host \
--runtime=nvidia \
vllm/vllm-openai:latest \
--model $model \
--dtype bfloat16 \
--quantization bitsandbytes \
--load-format bitsandbytes \
--tensor-parallel-size 4
vllm is stuck at loading in both cases:
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.42.06 Driver Version: 555.42.06 CUDA Version: 12.5 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA A10G Off | 00000000:00:1B.0 Off | 0 |
| 0% 31C P0 65W / 300W | 516MiB / 23028MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA A10G Off | 00000000:00:1C.0 Off | 0 |
| 0% 31C P0 63W / 300W | 524MiB / 23028MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 2 NVIDIA A10G Off | 00000000:00:1D.0 Off | 0 |
| 0% 32C P0 67W / 300W | 524MiB / 23028MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 3 NVIDIA A10G Off | 00000000:00:1E.0 Off | 0 |
| 0% 31C P0 66W / 300W | 484MiB / 23028MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
vllm log:
WARNING 11-08 11:49:58 multiproc_gpu_executor.py:53] Reducing Torch parallelism from 24 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed.
INFO 11-08 11:49:58 custom_cache_manager.py:17] Setting Triton cache manager to: vllm.triton_utils.custom_cache_manager:CustomCacheManager
(VllmWorkerProcess pid=36253) INFO 11-08 11:50:03 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=36252) INFO 11-08 11:50:03 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=36254) INFO 11-08 11:50:03 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
INFO 11-08 11:50:04 utils.py:1008] Found nccl from library libnccl.so.2
INFO 11-08 11:50:04 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=36252) INFO 11-08 11:50:04 utils.py:1008] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=36253) INFO 11-08 11:50:04 utils.py:1008] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=36254) INFO 11-08 11:50:04 utils.py:1008] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=36252) INFO 11-08 11:50:04 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=36253) INFO 11-08 11:50:04 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=36254) INFO 11-08 11:50:04 pynccl.py:63] vLLM is using nccl==2.20.5
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.
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Comments: 18 (7 by maintainers)
Hi @youkaichao and @DarkLight1337, It works now, after reinstalling cuda and nvidia drivers with latest version. I also reset vllm. Thank you for your help and guidance.
I was able to solve it using test.py provided with the debugging docs.