[Bug]: error in examples/online_serving/openai_transcription_client.py

[farouk09]

Your current environment

Hi everyone,

I'm trying to run the code in examples/online_serving/openai_transcription_client.py

I'm using vllm 0.8.4

🐛 Describe the bug

INFO 04-28 17:06:48 [init.py:239] Automatically detected platform cuda.
transcription result: The first words I spoke in the original phonograph, a little piece of practical poetry. Mary had a little lamb, its streets were quite as slow, and everywhere that Mary went the lamb was sure to go.
transcription result: Traceback (most recent call last):
File "/home/aptikal/abdalfar/InterviewSim/vllm_project/openai_transcription_client.py", line 66, in
asyncio.run(stream_openai_response())
File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/aptikal/abdalfar/InterviewSim/vllm_project/openai_transcription_client.py", line 60, in stream_openai_response
content = chunk['choices'][0].get('delta',
~~~~~^^^^^^^^^^^
KeyError: 'choices'

Any idea how to solve this ?
Thank you

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.

[DarkLight1337]

cc @NickLucche

[NickLucche]

I can't quite reproduce your issue on the version you specified.
Could you kindly share the server start command as well as the output of collect_env?

[farouk09]

Thank you for the reply, the command to start the server : uv run vllm serve openai/whisper-large-v3-turbo --api-key "EMPTY" . here is the output of collect_env :

INFO 04-28 21:17:01 [__init__.py:239] Automatically detected platform cuda.
Collecting environment information...
/home/aptikal/abdalfar/InterviewSim/vllm_project/.venv/lib/python3.11/site-packages/_distutils_hack/__init__.py:30: UserWarning: Setuptools is replacing distutils. Support for replacing an already imported distutils is deprecated. In the future, this condition will fail. Register concerns at https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml
  warnings.warn(
uv is set
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14) 12.2.0
Clang version: 14.0.6
CMake version: version 3.25.1
Libc version: glibc-2.36

Python version: 3.11.2 (main, Nov 30 2024, 21:22:50) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-6.1.0-26-amd64-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA RTX A6000
Nvidia driver version: 550.67
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture :                          x86_64
Mode(s) opératoire(s) des processeurs : 32-bit, 64-bit
Tailles des adresses:                   46 bits physical, 48 bits virtual
Boutisme :                              Little Endian
Processeur(s) :                         32
Liste de processeur(s) en ligne :       0-31
Identifiant constructeur :              GenuineIntel
Nom de modèle :                         Intel(R) Xeon(R) CPU E5-2640 v3 @ 2.60GHz
Famille de processeur :                 6
Modèle :                                63
Thread(s) par cœur :                    2
Cœur(s) par socket :                    8
Socket(s) :                             2
Révision :                              2
multiplication des MHz du/des CPU(s) :  41%
Vitesse maximale du processeur en MHz : 3400,0000
Vitesse minimale du processeur en MHz : 1200,0000
BogoMIPS :                              5199,84
Drapeaux :                              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 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 cpuid_fault epb invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc dtherm ida arat pln pts md_clear flush_l1d
Virtualisation :                        VT-x
Cache L1d :                             512 KiB (16 instances)
Cache L1i :                             512 KiB (16 instances)
Cache L2 :                              4 MiB (16 instances)
Cache L3 :                              40 MiB (2 instances)
Nœud(s) NUMA :                          2
Nœud NUMA 0 de processeur(s) :          0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30
Nœud NUMA 1 de processeur(s) :          1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31
Vulnérabilité Gather data sampling :    Not affected
Vulnérabilité Itlb multihit :           KVM: Mitigation: VMX disabled
Vulnérabilité L1tf :                    Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnérabilité Mds :                     Mitigation; Clear CPU buffers; SMT vulnerable
Vulnérabilité Meltdown :                Mitigation; PTI
Vulnérabilité Mmio stale data :         Mitigation; Clear CPU buffers; SMT vulnerable
Vulnérabilité Reg file data sampling :  Not affected
Vulnérabilité Retbleed :                Not affected
Vulnérabilité Spec rstack overflow :    Not affected
Vulnérabilité Spec store bypass :       Mitigation; Speculative Store Bypass disabled via prctl
Vulnérabilité Spectre v1 :              Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnérabilité Spectre v2 :              Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnérabilité Srbds :                   Not affected
Vulnérabilité Tsx async abort :         Not affected

Versions of relevant libraries:
[pip3] numpy==2.2.5
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.4.0
[pip3] sentence-transformers==4.1.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.51.3
[pip3] triton==3.2.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.4
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
        GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      0,2,4,6,8,10    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

NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY