Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: Whisper online benchmark with profiling error: TypeError: multi_modal_content must be a dict containing 'audio' [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#38586•Fetched 2026-04-08 01:53:17
View on GitHub
Comments
2
Participants
2
Timeline
6
Reactions
0
Author
AdityaKulshresthaAdityaKulshrestha
Participants
AdityaKulshresthaAdityaKulshresthaKrxGuKrxGu
Timeline (top)
commented ×2labeled ×1mentioned ×1renamed ×1

Error Message

INFO 03-30 20:45:39 [importing.py:44] Triton is installed but 0 active driver(s) found (expected 1). Disabling Triton to prevent runtime errors. INFO 03-30 20:45:39 [importing.py:68] Triton not installed or not compatible; certain GPU-related functions will not be available. Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x78bdb9f76d40>, trust_remote_code=False, seed=0, num_prompts=32, dataset_name='hf', no_stream=True, dataset_path='openslr/librispeech_asr', no_oversample=True, skip_chat_template=False, enable_multimodal_chat=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, asr_max_audio_len_sec=inf, asr_min_audio_len_sec=0.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset='clean', hf_split='test', hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai-audio', base_url=None, host='0.0.0.0', port=8001, endpoint='/v1/audio/transcriptions', header=None, max_concurrency=32, model='openai/whisper-medium', input_len=None, output_len=None, tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=inf, burstiness=1.0, disable_tqdm=False, num_warmups=0, profile=True, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-951cd6ae-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None, skip_tokenizer_init=False, insecure=False, plot_timeline=False, timeline_itl_thresholds=[25.0, 50.0], plot_dataset_stats=False) Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 27023.70it/s] Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 40762.62it/s] INFO 03-30 20:45:45 [datasets.py:3201] Number of audio samples: 32 INFO 03-30 20:45:45 [datasets.py:3206] Audio duration statistics (s): avg=8.20, min=2.02, max=28.41, median=5.71 INFO 03-30 20:45:45 [datasets.py:232] Skipping oversampling. Total samples: 32. WARNING: vllm bench serve no longer sets temperature==0 (greedy) in requests by default. The default will be determined on the server side and can be model/API specific. For the old behavior, include --temperature=0. Starting initial single prompt test run... Waiting for endpoint to become up in 600 seconds | | 00:08 elapsed, 2004:05:41 remaining Initial test run completed. Starting main benchmark run... Starting profiler... Profiler started Traffic request rate: inf Burstiness factor: 1.0 (Poisson process) Maximum request concurrency: 32 100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [01:38<00:00, 3.07s/it] tip: install termplotlib and gnuplot to plot the metrics ============ Serving Benchmark Result ============ Successful requests: 32
Failed requests: 0
Maximum request concurrency: 32
Benchmark duration (s): 98.24
Total input tokens: 224
Total generated tokens: 892
Request throughput (req/s): 0.33
Output token throughput (tok/s): 9.08
Peak output token throughput (tok/s): 27.00
Peak concurrent requests: 32.00
RTFx (Inverse Real-Time Factor): 2.67
Total token throughput (tok/s): 11.36
---------------Time to First Token---------------- Mean TTFT (ms): 16671.34
Median TTFT (ms): 16622.73
P99 TTFT (ms): 31308.84
-----Time per Output Token (excl. 1st token)------ Mean TPOT (ms): 1382.33
Median TPOT (ms): 1401.16
P99 TPOT (ms): 1912.72
---------------Inter-token Latency---------------- Mean ITL (ms): 1197.96
Median ITL (ms): 1059.75
P99 ITL (ms): 1984.74

Stopping profiler... Traceback (most recent call last): File ".venv/bin/vllm", line 10, in <module> sys.exit(main()) ^^^^^^ File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 73, in main args.dispatch_function(args) File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/benchmark/serve.py", line 21, in cmd main(args) File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1609, in main return asyncio.run(main_async(args)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run return runner.run(main) ^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1773, in main_async benchmark_result = await benchmark( ^^^^^^^^^^^^^^^^ File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1104, in benchmark profile_output = await request_func( ^^^^^^^^^^^^^^^^^^^ File ".venv/lib/python3.12/site-packages/vllm/benchmarks/lib/endpoint_request_func.py", line 417, in async_request_openai_audio raise TypeError("multi_modal_content must be a dict containing 'audio'")

Fix Action

Fix / Workaround

INFO 03-30 20:45:39 [importing.py:44] Triton is installed but 0 active driver(s) found (expected 1). Disabling Triton to prevent runtime errors.
INFO 03-30 20:45:39 [importing.py:68] Triton not installed or not compatible; certain GPU-related functions will not be available.
Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x78bdb9f76d40>, trust_remote_code=False, seed=0, num_prompts=32, dataset_name='hf', no_stream=True, dataset_path='openslr/librispeech_asr', no_oversample=True, skip_chat_template=False, enable_multimodal_chat=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, asr_max_audio_len_sec=inf, asr_min_audio_len_sec=0.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset='clean', hf_split='test', hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai-audio', base_url=None, host='0.0.0.0', port=8001, endpoint='/v1/audio/transcriptions', header=None, max_concurrency=32, model='openai/whisper-medium', input_len=None, output_len=None, tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=inf, burstiness=1.0, disable_tqdm=False, num_warmups=0, profile=True, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-951cd6ae-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None, skip_tokenizer_init=False, insecure=False, plot_timeline=False, timeline_itl_thresholds=[25.0, 50.0], plot_dataset_stats=False)
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 27023.70it/s]
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 40762.62it/s]
INFO 03-30 20:45:45 [datasets.py:3201] Number of audio samples: 32
INFO 03-30 20:45:45 [datasets.py:3206] Audio duration statistics (s): avg=8.20, min=2.02, max=28.41, median=5.71
INFO 03-30 20:45:45 [datasets.py:232] Skipping oversampling. Total samples: 32.
WARNING: vllm bench serve no longer sets temperature==0 (greedy) in requests by default. The default will be determined on the server side and can be model/API specific. For the old behavior, include --temperature=0.
Starting initial single prompt test run...
Waiting for endpoint to become up in 600 seconds
 |                                                                                                  | 00:08 elapsed, 2004:05:41 remaining
Initial test run completed.
Starting main benchmark run...
Starting profiler...
Profiler started
Traffic request rate: inf
Burstiness factor: 1.0 (Poisson process)
Maximum request concurrency: 32
100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [01:38<00:00,  3.07s/it]
tip: install termplotlib and gnuplot to plot the metrics
============ Serving Benchmark Result ============
Successful requests:                     32        
Failed requests:                         0         
Maximum request concurrency:             32        
Benchmark duration (s):                  98.24     
Total input tokens:                      224       
Total generated tokens:                  892       
Request throughput (req/s):              0.33      
Output token throughput (tok/s):         9.08      
Peak output token throughput (tok/s):    27.00     
Peak concurrent requests:                32.00     
RTFx (Inverse Real-Time Factor):         2.67      
Total token throughput (tok/s):          11.36     
---------------Time to First Token----------------
Mean TTFT (ms):                          16671.34  
Median TTFT (ms):                        16622.73  
P99 TTFT (ms):                           31308.84  
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          1382.33   
Median TPOT (ms):                        1401.16   
P99 TPOT (ms):                           1912.72   
---------------Inter-token Latency----------------
Mean ITL (ms):                           1197.96   
Median ITL (ms):                         1059.75   
P99 ITL (ms):                            1984.74   
==================================================
Stopping profiler...
Traceback (most recent call last):
  File ".venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 73, in main
    args.dispatch_function(args)
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/benchmark/serve.py", line 21, in cmd
    main(args)
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1609, in main
    return asyncio.run(main_async(args))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1773, in main_async
    benchmark_result = await benchmark(
                       ^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1104, in benchmark
    profile_output = await request_func(
                     ^^^^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/lib/endpoint_request_func.py", line 417, in async_request_openai_audio
    raise TypeError("multi_modal_content must be a dict containing 'audio'")

==============================
          CPU Info
==============================
Architecture:                            x86_64
CPU op-mode(s):                          32-bit, 64-bit
Address sizes:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) 6767P
CPU family:                              6
Model:                                   173
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                1
CPU(s) scaling MHz:                      40%
CPU max MHz:                             3900.0000
CPU min MHz:                             800.0000
BogoMIPS:                                4800.00
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 tsc_known_freq 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 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities ibpb_exit_to_user
Virtualization:                          VT-x
L1d cache:                               6 MiB (128 instances)
L1i cache:                               8 MiB (128 instances)
L2 cache:                                256 MiB (128 instances)
L3 cache:                                672 MiB (2 instances)
NUMA node(s):                            4
NUMA node0 CPU(s):                       0-31,128-159
NUMA node1 CPU(s):                       32-63,160-191
NUMA node2 CPU(s):                       64-95,192-223
NUMA node3 CPU(s):                       96-127,224-255
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: 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:                  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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS Not affected; BHI BHI_DIS_S
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

Code Example

INFO 03-30 20:45:39 [importing.py:44] Triton is installed but 0 active driver(s) found (expected 1). Disabling Triton to prevent runtime errors.
INFO 03-30 20:45:39 [importing.py:68] Triton not installed or not compatible; certain GPU-related functions will not be available.
Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x78bdb9f76d40>, trust_remote_code=False, seed=0, num_prompts=32, dataset_name='hf', no_stream=True, dataset_path='openslr/librispeech_asr', no_oversample=True, skip_chat_template=False, enable_multimodal_chat=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, asr_max_audio_len_sec=inf, asr_min_audio_len_sec=0.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset='clean', hf_split='test', hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai-audio', base_url=None, host='0.0.0.0', port=8001, endpoint='/v1/audio/transcriptions', header=None, max_concurrency=32, model='openai/whisper-medium', input_len=None, output_len=None, tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=inf, burstiness=1.0, disable_tqdm=False, num_warmups=0, profile=True, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-951cd6ae-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None, skip_tokenizer_init=False, insecure=False, plot_timeline=False, timeline_itl_thresholds=[25.0, 50.0], plot_dataset_stats=False)
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 27023.70it/s]
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 40762.62it/s]
INFO 03-30 20:45:45 [datasets.py:3201] Number of audio samples: 32
INFO 03-30 20:45:45 [datasets.py:3206] Audio duration statistics (s): avg=8.20, min=2.02, max=28.41, median=5.71
INFO 03-30 20:45:45 [datasets.py:232] Skipping oversampling. Total samples: 32.
WARNING: vllm bench serve no longer sets temperature==0 (greedy) in requests by default. The default will be determined on the server side and can be model/API specific. For the old behavior, include --temperature=0.
Starting initial single prompt test run...
Waiting for endpoint to become up in 600 seconds
 |                                                                                                  | 00:08 elapsed, 2004:05:41 remaining
Initial test run completed.
Starting main benchmark run...
Starting profiler...
Profiler started
Traffic request rate: inf
Burstiness factor: 1.0 (Poisson process)
Maximum request concurrency: 32
100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [01:38<00:00,  3.07s/it]
tip: install termplotlib and gnuplot to plot the metrics
============ Serving Benchmark Result ============
Successful requests:                     32        
Failed requests:                         0         
Maximum request concurrency:             32        
Benchmark duration (s):                  98.24     
Total input tokens:                      224       
Total generated tokens:                  892       
Request throughput (req/s):              0.33      
Output token throughput (tok/s):         9.08      
Peak output token throughput (tok/s):    27.00     
Peak concurrent requests:                32.00     
RTFx (Inverse Real-Time Factor):         2.67      
Total token throughput (tok/s):          11.36     
---------------Time to First Token----------------
Mean TTFT (ms):                          16671.34  
Median TTFT (ms):                        16622.73  
P99 TTFT (ms):                           31308.84  
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          1382.33   
Median TPOT (ms):                        1401.16   
P99 TPOT (ms):                           1912.72   
---------------Inter-token Latency----------------
Mean ITL (ms):                           1197.96   
Median ITL (ms):                         1059.75   
P99 ITL (ms):                            1984.74   
==================================================
Stopping profiler...
Traceback (most recent call last):
  File ".venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 73, in main
    args.dispatch_function(args)
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/benchmark/serve.py", line 21, in cmd
    main(args)
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1609, in main
    return asyncio.run(main_async(args))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1773, in main_async
    benchmark_result = await benchmark(
                       ^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1104, in benchmark
    profile_output = await request_func(
                     ^^^^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/lib/endpoint_request_func.py", line 417, in async_request_openai_audio
    raise TypeError("multi_modal_content must be a dict containing 'audio'")

---

==============================
        System Info
==============================
OS                           : Ubuntu 24.04.3 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : 18.1.3 (1ubuntu1)
CMake version                : version 3.28.3
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cpu
Is debug build               : False
CUDA used to build PyTorch   : None
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-106-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : No CUDA
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : No CUDA
Nvidia driver version        : No CUDA
cuDNN version                : No CUDA
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                            x86_64
CPU op-mode(s):                          32-bit, 64-bit
Address sizes:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) 6767P
CPU family:                              6
Model:                                   173
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                1
CPU(s) scaling MHz:                      40%
CPU max MHz:                             3900.0000
CPU min MHz:                             800.0000
BogoMIPS:                                4800.00
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 tsc_known_freq 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 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities ibpb_exit_to_user
Virtualization:                          VT-x
L1d cache:                               6 MiB (128 instances)
L1i cache:                               8 MiB (128 instances)
L2 cache:                                256 MiB (128 instances)
L3 cache:                                672 MiB (2 instances)
NUMA node(s):                            4
NUMA node0 CPU(s):                       0-31,128-159
NUMA node1 CPU(s):                       32-63,160-191
NUMA node2 CPU(s):                       64-95,192-223
NUMA node3 CPU(s):                       96-127,224-255
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: 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:                  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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS Not affected; BHI BHI_DIS_S
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] onnxruntime==1.24.4
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0+cpu
[pip3] torchaudio==2.11.0+cpu
[pip3] torchcodec==0.10.0
[pip3] torchvision==0.25.0+cpu
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1rc1.dev252+gb5e608258 (git sha: b5e608258)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     Environment Variables
==============================
VLLM_CPU_OMP_THREADS_BIND=0-31|32-63
OMP_NUM_THREADS=32
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

---

export LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$VIRTUAL_ENV/lib/libiomp5.so"
  OMP_NUM_THREADS=32 VLLM_CPU_OMP_THREADS_BIND='0-31|32-63' vllm serve openai/whisper-medium \
          --host 0.0.0.0 \
          --port 8001 \
          --dtype bfloat16 \
          --tensor-parallel-size 2 \
          --max-model-len 448 \
          --max-num-seqs 128 \
          --profiler-config '{"profiler": "torch", "torch_profiler_dir": "./vllm_profile", "torch_profiler_record_shapes": true, "torch_profiler_with_flops": true}'

---

vllm bench serve \
          --backend openai-audio \
          --model openai/whisper-medium \
          --endpoint /v1/audio/transcriptions \
          --host 0.0.0.0 \
          --port 8001 \
          --dataset-name hf \
          --dataset-path openslr/librispeech_asr \
          --hf-subset clean \
          --hf-split test \
          --num-prompts 32 \
          --max-concurrency 32 \
          --no-stream \
          --no-oversample \
          --ready-check-timeout-sec 600 \
          --profile
RAW_BUFFERClick to expand / collapse

Your current environment

The vLLM Benchmarking with profiling is failing for Whisper model in online benchmarking.

INFO 03-30 20:45:39 [importing.py:44] Triton is installed but 0 active driver(s) found (expected 1). Disabling Triton to prevent runtime errors.
INFO 03-30 20:45:39 [importing.py:68] Triton not installed or not compatible; certain GPU-related functions will not be available.
Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x78bdb9f76d40>, trust_remote_code=False, seed=0, num_prompts=32, dataset_name='hf', no_stream=True, dataset_path='openslr/librispeech_asr', no_oversample=True, skip_chat_template=False, enable_multimodal_chat=False, disable_shuffle=False, custom_output_len=256, spec_bench_output_len=256, spec_bench_category=None, sonnet_input_len=550, sonnet_output_len=150, sonnet_prefix_len=200, sharegpt_output_len=None, blazedit_min_distance=0.0, blazedit_max_distance=1.0, asr_max_audio_len_sec=inf, asr_min_audio_len_sec=0.0, random_input_len=1024, random_output_len=128, random_range_ratio=0.0, random_prefix_len=0, random_batch_size=1, no_reranker=False, random_mm_base_items_per_request=1, random_mm_num_mm_items_range_ratio=0.0, random_mm_limit_mm_per_prompt={'image': 255, 'video': 1}, random_mm_bucket_config={(256, 256, 1): 0.5, (720, 1280, 1): 0.5, (720, 1280, 16): 0.0}, hf_subset='clean', hf_split='test', hf_name=None, hf_output_len=None, prefix_repetition_prefix_len=256, prefix_repetition_suffix_len=256, prefix_repetition_num_prefixes=10, prefix_repetition_output_len=128, label=None, backend='openai-audio', base_url=None, host='0.0.0.0', port=8001, endpoint='/v1/audio/transcriptions', header=None, max_concurrency=32, model='openai/whisper-medium', input_len=None, output_len=None, tokenizer=None, tokenizer_mode='auto', use_beam_search=False, logprobs=None, request_rate=inf, burstiness=1.0, disable_tqdm=False, num_warmups=0, profile=True, save_result=False, save_detailed=False, append_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics=None, metric_percentiles='99', goodput=None, request_id_prefix='bench-951cd6ae-', top_p=None, top_k=None, min_p=None, temperature=None, frequency_penalty=None, presence_penalty=None, repetition_penalty=None, served_model_name=None, lora_modules=None, ramp_up_strategy=None, ramp_up_start_rps=None, ramp_up_end_rps=None, ready_check_timeout_sec=600, extra_body=None, skip_tokenizer_init=False, insecure=False, plot_timeline=False, timeline_itl_thresholds=[25.0, 50.0], plot_dataset_stats=False)
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 27023.70it/s]
Resolving data files: 100%|███████████████████████████████████████████████████████████████████████████| 48/48 [00:00<00:00, 40762.62it/s]
INFO 03-30 20:45:45 [datasets.py:3201] Number of audio samples: 32
INFO 03-30 20:45:45 [datasets.py:3206] Audio duration statistics (s): avg=8.20, min=2.02, max=28.41, median=5.71
INFO 03-30 20:45:45 [datasets.py:232] Skipping oversampling. Total samples: 32.
WARNING: vllm bench serve no longer sets temperature==0 (greedy) in requests by default. The default will be determined on the server side and can be model/API specific. For the old behavior, include --temperature=0.
Starting initial single prompt test run...
Waiting for endpoint to become up in 600 seconds
 |                                                                                                  | 00:08 elapsed, 2004:05:41 remaining
Initial test run completed.
Starting main benchmark run...
Starting profiler...
Profiler started
Traffic request rate: inf
Burstiness factor: 1.0 (Poisson process)
Maximum request concurrency: 32
100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [01:38<00:00,  3.07s/it]
tip: install termplotlib and gnuplot to plot the metrics
============ Serving Benchmark Result ============
Successful requests:                     32        
Failed requests:                         0         
Maximum request concurrency:             32        
Benchmark duration (s):                  98.24     
Total input tokens:                      224       
Total generated tokens:                  892       
Request throughput (req/s):              0.33      
Output token throughput (tok/s):         9.08      
Peak output token throughput (tok/s):    27.00     
Peak concurrent requests:                32.00     
RTFx (Inverse Real-Time Factor):         2.67      
Total token throughput (tok/s):          11.36     
---------------Time to First Token----------------
Mean TTFT (ms):                          16671.34  
Median TTFT (ms):                        16622.73  
P99 TTFT (ms):                           31308.84  
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          1382.33   
Median TPOT (ms):                        1401.16   
P99 TPOT (ms):                           1912.72   
---------------Inter-token Latency----------------
Mean ITL (ms):                           1197.96   
Median ITL (ms):                         1059.75   
P99 ITL (ms):                            1984.74   
==================================================
Stopping profiler...
Traceback (most recent call last):
  File ".venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 73, in main
    args.dispatch_function(args)
  File ".venv/lib/python3.12/site-packages/vllm/entrypoints/cli/benchmark/serve.py", line 21, in cmd
    main(args)
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1609, in main
    return asyncio.run(main_async(args))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1773, in main_async
    benchmark_result = await benchmark(
                       ^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/serve.py", line 1104, in benchmark
    profile_output = await request_func(
                     ^^^^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.12/site-packages/vllm/benchmarks/lib/endpoint_request_func.py", line 417, in async_request_openai_audio
    raise TypeError("multi_modal_content must be a dict containing 'audio'")
<summary>The output of <code>python collect_env.py</code></summary> 
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.3 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : 18.1.3 (1ubuntu1)
CMake version                : version 3.28.3
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cpu
Is debug build               : False
CUDA used to build PyTorch   : None
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-106-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : No CUDA
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : No CUDA
Nvidia driver version        : No CUDA
cuDNN version                : No CUDA
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                            x86_64
CPU op-mode(s):                          32-bit, 64-bit
Address sizes:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) 6767P
CPU family:                              6
Model:                                   173
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                1
CPU(s) scaling MHz:                      40%
CPU max MHz:                             3900.0000
CPU min MHz:                             800.0000
BogoMIPS:                                4800.00
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 tsc_known_freq 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 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities ibpb_exit_to_user
Virtualization:                          VT-x
L1d cache:                               6 MiB (128 instances)
L1i cache:                               8 MiB (128 instances)
L2 cache:                                256 MiB (128 instances)
L3 cache:                                672 MiB (2 instances)
NUMA node(s):                            4
NUMA node0 CPU(s):                       0-31,128-159
NUMA node1 CPU(s):                       32-63,160-191
NUMA node2 CPU(s):                       64-95,192-223
NUMA node3 CPU(s):                       96-127,224-255
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: 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:                  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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS Not affected; BHI BHI_DIS_S
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] onnxruntime==1.24.4
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0+cpu
[pip3] torchaudio==2.11.0+cpu
[pip3] torchcodec==0.10.0
[pip3] torchvision==0.25.0+cpu
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1rc1.dev252+gb5e608258 (git sha: b5e608258)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     Environment Variables
==============================
VLLM_CPU_OMP_THREADS_BIND=0-31|32-63
OMP_NUM_THREADS=32
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
</details>

🐛 Describe the bug

Steps to reproduce:

  1. Start the server:
export LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$VIRTUAL_ENV/lib/libiomp5.so"
OMP_NUM_THREADS=32 VLLM_CPU_OMP_THREADS_BIND='0-31|32-63' vllm serve openai/whisper-medium \
        --host 0.0.0.0 \
        --port 8001 \
        --dtype bfloat16 \
        --tensor-parallel-size 2 \
        --max-model-len 448 \
        --max-num-seqs 128 \
        --profiler-config '{"profiler": "torch", "torch_profiler_dir": "./vllm_profile", "torch_profiler_record_shapes": true, "torch_profiler_with_flops": true}'
  1. Start benchmarking:
vllm bench serve \
        --backend openai-audio \
        --model openai/whisper-medium \
        --endpoint /v1/audio/transcriptions \
        --host 0.0.0.0 \
        --port 8001 \
        --dataset-name hf \
        --dataset-path openslr/librispeech_asr \
        --hf-subset clean \
        --hf-split test \
        --num-prompts 32 \
        --max-concurrency 32 \
        --no-stream \
        --no-oversample \
        --ready-check-timeout-sec 600 \
        --profile

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.

extent analysis

Fix Plan

The error message indicates that multi_modal_content must be a dict containing 'audio'. To fix this issue, we need to modify the async_request_openai_audio function in endpoint_request_func.py to ensure that multi_modal_content is a dict with the required 'audio' key.

Here are the steps to fix the issue:

  • Modify the async_request_openai_audio function to check if multi_modal_content is a dict and contains the 'audio' key.
  • If multi_modal_content is not a dict or does not contain the 'audio' key, create a new dict with the required 'audio' key and assign it to multi_modal_content.

Example code:

def async_request_openai_audio(self, *args, **kwargs):
    # ... existing code ...
    if not isinstance(multi_modal_content, dict) or 'audio' not in multi_modal_content:
        multi_modal_content = {'audio': multi_modal_content}
    # ... existing code ...

Alternatively, you can also modify the code that calls async_request_openai_audio to ensure that multi_modal_content is a dict with the required 'audio' key.

Verification

To verify that the fix worked, run the benchmarking command again and check if the error message is resolved. You can also add print statements or use a debugger to verify that multi_modal_content is a dict with the required 'audio' key.

Extra Tips

  • Make sure to test the fix thoroughly to ensure that it does not introduce any new issues.
  • Consider adding error handling to handle cases where multi_modal_content is not a dict or does not contain the required 'audio' key.
  • If you are using a version of the vllm library that is older than the one that introduced the fix, you may need to upgrade to a newer version to get the fix.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#database connection#vector store#runtime error#environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING