[Usage, bug]: vLLM Docker | ValueError: OpenTelemetry packages must be installed before configuring 'otlp_traces_endpoint' during vLLM startup

[vipulgote1999]

Your current environment

binishb.ttl@vzneuronsr01:~/Vipul$ python3.10 collect_env_vllm.py
Collecting environment information...
WARNING 08-20 12:51:20 ray_utils.py:34] Failed to import Ray with ModuleNotFoundError("No module named 'ray.core'"). For distributed inference, please install Ray with `pip install ray pandas pyarrow`.
PyTorch version: 2.1.2+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.26.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-113-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 11.5.119
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A100-PCIE-40GB
GPU 1: NVIDIA A100-PCIE-40GB

Nvidia driver version: 535.183.01
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.6
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):                             16
On-line CPU(s) list:                0-15
Vendor ID:                          GenuineIntel
Model name:                         Intel Xeon Processor (Cascadelake)
CPU family:                         6
Model:                              85
Thread(s) per core:                 1
Core(s) per socket:                 16
Socket(s):                          1
Stepping:                           5
BogoMIPS:                           5187.81
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq md_clear arch_capabilities
Hypervisor vendor:                  KVM
Virtualization type:                full
L1d cache:                          512 KiB (16 instances)
L1i cache:                          512 KiB (16 instances)
L2 cache:                           64 MiB (16 instances)
NUMA node(s):                       1
NUMA node0 CPU(s):                  0-15
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit:        KVM: Mitigation: VMX unsupported
Vulnerability L1tf:                 Mitigation; PTE Inversion
Vulnerability Mds:                  Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:             Mitigation; PTI
Vulnerability Mmio stale data:      Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed:             Mitigation; IBRS
Vulnerability Spec rstack overflow: 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; IBRS; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Syscall hardening, KVM SW loop
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Mitigation; Clear CPU buffers; SMT Host state unknown

Versions of relevant libraries:
[pip3] ctransformers==0.2.23
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.23.0
[pip3] numpyencoder==0.3.0
[pip3] nvidia-cublas-cu11==11.10.3.66
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu11==11.7.101
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu11==11.7.99
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu11==11.7.99
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu11==8.5.0.96
[pip3] nvidia-cudnn-cu12==8.9.2.26
[pip3] nvidia-cufft-cu11==10.9.0.58
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu11==10.2.10.91
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu11==11.4.0.1
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu11==11.7.4.91
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.535.133
[pip3] nvidia-nccl-cu11==2.14.3
[pip3] nvidia-nccl-cu12==2.18.1
[pip3] nvidia-nvjitlink-cu12==12.3.101
[pip3] nvidia-nvtx-cu11==11.7.91
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pynvml==11.5.0
[pip3] pyzmq==25.1.1
[pip3] sentence-transformers==2.2.2
[pip3] torch==2.1.2
[pip3] torchdata==0.7.1
[pip3] torchtext==0.16.2
[pip3] torchvision==0.16.2
[pip3] transformers==4.36.2
[pip3] triton==2.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: N/A
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      PHB     0-15    0               N/A
GPU1    PHB      X      0-15    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

How would you like to use vllm

Description: When spinning up new docker container it is showing error for missing package.

Docker run command:
docker run -d --runtime nvidia --gpus all -v ~/Vipul/nltk_data:/home/user/nltk_data -v /home/binishb.ttl/Meta-Llama-3.1-8B-Instruct/:/root/Meta-Llama-3.1-8B-Instruct --env "HUGGING_FACE_HUB_TOKEN=xxxxxxxxxxxxxxxxx" -p 8514:8514 --ipc=host --env "CUDA_VISIBLE_DEVICES=1" --entrypoint "python3" vllm/vllm-openai:v0.5.4 -m vllm.entrypoints.openai.api_server --model /root/Meta-Llama-3.1-8B-Instruct --gpu-memory-utilization 0.9 --port 8514 --max-model-len 64000 --seed 42 --otlp-traces-endpoint "grpc://xxxxxxxxxx:4317" --enable-prefix-caching

Error:

While running the vLLM API server (v0.5.4) using Docker, the following error is encountered during initialization when trying to configure the otlp_traces_endpoint:
_ValueError: OpenTelemetry packages must be installed before configuring 'otlp_traces_endpoint'_

Docker logs

binishb.ttl@vzneuronsr01:~$ docker logs fc2b9c21e998
INFO 08-20 07:15:58 api_server.py:339] vLLM API server version 0.5.4
INFO 08-20 07:15:58 api_server.py:340] args: Namespace(host=None, port=8514, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, model='/root/Meta-Llama-3.1-8B-Instruct', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, download_dir=None, load_format='auto', dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=64000, guided_decoding_backend='outlines', distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=1, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=True, disable_sliding_window=False, use_v2_block_manager=False, num_lookahead_slots=0, seed=42, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, enforce_eager=False, max_context_len_to_capture=None, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, num_speculative_tokens=None, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint='grpc://xxxxxxxxxxx:4317', engine_use_ray=False, disable_log_requests=False, max_log_len=None)
WARNING 08-20 07:15:58 config.py:1454] Casting torch.bfloat16 to torch.float16.
WARNING 08-20 07:15:58 arg_utils.py:776] The model has a long context length (64000). This may cause OOM errors during the initial memory profiling phase, or result in low performance due to small KV cache space. Consider setting --max-model-len to a smaller value.
Process Process-1:
Traceback (most recent call last):
  File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/rpc/server.py", line 217, in run_rpc_server
    server = AsyncEngineRPCServer(async_engine_args, usage_context, port)
  File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/rpc/server.py", line 25, in __init__
    self.engine = AsyncLLMEngine.from_engine_args(async_engine_args,
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 462, in from_engine_args
    engine_config = engine_args.create_engine_config()
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/arg_utils.py", line 852, in create_engine_config
    observability_config = ObservabilityConfig(
  File "<string>", line 4, in __init__
  File "/usr/local/lib/python3.10/dist-packages/vllm/config.py", line 1615, in __post_init__
    raise ValueError("OpenTelemetry packages must be installed before "
ValueError: OpenTelemetry packages must be installed before configuring 'otlp_traces_endpoint'

Potential Fix:

It seems like the issue arises because the required OpenTelemetry packages are missing. A possible solution could be either:

1. Adding a check during startup to ensure the necessary packages are installed if the otlp_traces_endpoint is configured.
2. Automatically disabling observability features if the packages are not available, and logging a warning instead of raising an error.
3. Adding pip install opentelemetry-sdk opentelemetry-api opentelemetry-exporter-otlp opentelemetry-semantic-conventions-ai

[K-Mistele]

seems like opentelemetry should just be added to requirements-common.txt, no?

[vipulgote1999]

Yes

[K-Mistele]

Yes

Have you create a PR for it already?

[vipulgote1999]

No pr needs to be created

[cermeng]

Otel usage doc: https://github.com/vllm-project/vllm/blob/main/examples/production_monitoring/Otel.md

According to #4687 (review), Otel packages are not included in official docker. You should install otel packages manually.