vllm - ✅(Solved) Fix [Bug]: vllm(g0e39202ca) vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function [1 pull requests, 1 comments, 2 participants]

vllm2026-04-13 08:56:04

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.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#39687•Fetched 2026-04-14 05:38:04

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Honghe

Participants

Honghe

ibrahim1023

Timeline (top)

commented ×1labeled ×1

Error Message

$ VLLM_USE_MODELSCOPE=true
vllm serve RedHatAI/gemma-4-31B-it-FP8_BLOCK
--port 8000
--tensor-parallel-size 4
--max-model-len 120000
--reasoning-parser gemma4
--enable-auto-tool-choice
--tool-call-parser gemma4
--kv-cache-dtype fp8
--gpu-memory-utilization 0.93
--limit-mm-per-prompt image=4,audio=1
--max-num-seqs 1 usage: vllm serve [model_tag] [options] vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function loads at 0x7a37a144c5e0>.

Fix Action

Fix / Workaround

============================== CPU Info

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): 256 On-line CPU(s) list: 0-255 Vendor ID: AuthenticAMD Model name: AMD EPYC 7B13 64-Core Processor CPU family: 25 Model: 1 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 1 Frequency boost: enabled CPU(s) scaling MHz: 48% CPU max MHz: 3541.3679 CPU min MHz: 1500.0000 BogoMIPS: 4491.45 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 rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm debug_swap ibpb_exit_to_user Virtualization: AMD-V L1d cache: 4 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 64 MiB (128 instances) L3 cache: 512 MiB (16 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-63,128-191 NUMA node1 CPU(s): 64-127,192-255 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: Mitigation; Safe RET 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; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsa: Vulnerable: Clear CPU buffers attempted, no microcode Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

PR fix notes

PR #39802: [Frontend] Improve parse_type error message for JSON dict CLI args

Repository: vllm-project/vllm
Author: hoobnn
State: open | merged: False
Link: https://github.com/vllm-project/vllm/pull/39802

Description (problem / solution / changelog)

Summary

Fixes #39687.

When a dict-typed CLI argument such as --limit-mm-per-prompt receives an invalid value (e.g. the legacy key=val,key=val form that was removed in #20969), parse_type in vllm/engine/arg_utils.py formats the error by interpolating json.loads directly into an f-string, producing:

vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function loads at 0x7a37a144c5e0>.

This is unreadable and gives no hint about the expected JSON syntax.

This PR reworks the ValueError branch in parse_type:

Special-case json.loads so the message explicitly mentions JSON, includes the underlying parse error, and shows a concrete example:

Value 'image=4,audio=1' is not valid JSON (Expecting value: line 1 column 1 (char 0)). Expected a JSON string, e.g. '{\"image\": 4, \"audio\": 1}'.

For other callables, use __qualname__ / __name__ instead of repr() so users see a type name rather than a <function ...> or <class ...> object address.

Pure error-message change — no behavioural difference for valid input.

Duplicate check

`gh issue view 39687` — no comments, no assignee.
`gh pr list --search "39687 in:body"` — no existing PR.
`gh pr list --search "parse_type error message"` — no overlapping PR.

Test Plan

`.venv/bin/python -m pytest tests/engine/test_arg_utils.py -q` — 56 passed (includes the two new regression tests below).
`.venv/bin/python -m pytest tests/engine/test_arg_utils.py::test_parse_type tests/engine/test_arg_utils.py::test_parse_type_json_error_hint tests/engine/test_arg_utils.py::test_parse_type_generic_error_message -v` — 6 passed.
`pre-commit run --files vllm/engine/arg_utils.py tests/engine/test_arg_utils.py` — all hooks passed (ruff check, ruff format, typos, mypy, SPDX, etc.).

New tests added in `tests/engine/test_arg_utils.py`:

`test_parse_type_json_error_hint` — regression for #39687; asserts the error message contains the offending value, mentions JSON, shows a `{"image"` example, and does not contain `<function`.
`test_parse_type_generic_error_message` — asserts non-JSON callables produce a readable type name and do not leak `<class ...>` repr.

Changed files

tests/engine/test_arg_utils.py (modified, +26/-1)
vllm/engine/arg_utils.py (modified, +10/-1)

Code Example

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar 20 2026, 00:33:26) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-6.8.0-107-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA GeForce RTX 4090
GPU 1: NVIDIA GeForce RTX 4090
GPU 2: NVIDIA GeForce RTX 4090
GPU 3: NVIDIA GeForce RTX 4090

Nvidia driver version        : 590.48.01
cuDNN version                : Could not collect
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:                           48 bits physical, 48 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 7B13 64-Core Processor
CPU family:                              25
Model:                                   1
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                1
Frequency boost:                         enabled
CPU(s) scaling MHz:                      48%
CPU max MHz:                             3541.3679
CPU min MHz:                             1500.0000
BogoMIPS:                                4491.45
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 rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm debug_swap ibpb_exit_to_user
Virtualization:                          AMD-V
L1d cache:                               4 MiB (128 instances)
L1i cache:                               4 MiB (128 instances)
L2 cache:                                64 MiB (128 instances)
L3 cache:                                512 MiB (16 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-63,128-191
NUMA node1 CPU(s):                       64-127,192-255
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:      Mitigation; Safe RET
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; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Vulnerable: Clear CPU buffers attempted, no microcode
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[pip3] numpy==2.4.4
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] pyzmq==27.1.0
[pip3] torch==2.11.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : dev
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    SYS     SYS     0-63,128-191    0               N/A
GPU1    NODE     X      SYS     SYS     0-63,128-191    0               N/A
GPU2    SYS     SYS      X      NODE    64-127,192-255  1               N/A
GPU3    SYS     SYS     NODE     X      64-127,192-255  1               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

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/usr/local/cuda/lib64:

---

$ VLLM_USE_MODELSCOPE=true \
vllm serve RedHatAI/gemma-4-31B-it-FP8_BLOCK \
  --port 8000 \
  --tensor-parallel-size 4 \
  --max-model-len 120000 \
  --reasoning-parser gemma4 \
  --enable-auto-tool-choice \
  --tool-call-parser gemma4 \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.93 \
  --limit-mm-per-prompt image=4,audio=1 \
  --max-num-seqs 1
usage: vllm serve [model_tag] [options]
vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function loads at 0x7a37a144c5e0>.

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar 20 2026, 00:33:26) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-6.8.0-107-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA GeForce RTX 4090
GPU 1: NVIDIA GeForce RTX 4090
GPU 2: NVIDIA GeForce RTX 4090
GPU 3: NVIDIA GeForce RTX 4090

Nvidia driver version        : 590.48.01
cuDNN version                : Could not collect
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:                           48 bits physical, 48 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 7B13 64-Core Processor
CPU family:                              25
Model:                                   1
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                1
Frequency boost:                         enabled
CPU(s) scaling MHz:                      48%
CPU max MHz:                             3541.3679
CPU min MHz:                             1500.0000
BogoMIPS:                                4491.45
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 rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm debug_swap ibpb_exit_to_user
Virtualization:                          AMD-V
L1d cache:                               4 MiB (128 instances)
L1i cache:                               4 MiB (128 instances)
L2 cache:                                64 MiB (128 instances)
L3 cache:                                512 MiB (16 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-63,128-191
NUMA node1 CPU(s):                       64-127,192-255
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:      Mitigation; Safe RET
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; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Vulnerable: Clear CPU buffers attempted, no microcode
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[pip3] numpy==2.4.4
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] pyzmq==27.1.0
[pip3] torch==2.11.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : dev
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    SYS     SYS     0-63,128-191    0               N/A
GPU1    NODE     X      SYS     SYS     0-63,128-191    0               N/A
GPU2    SYS     SYS      X      NODE    64-127,192-255  1               N/A
GPU3    SYS     SYS     NODE     X      64-127,192-255  1               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

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/usr/local/cuda/lib64:

</details>

🐛 Describe the bug

I run the following command by following docs https://docs.vllm.ai/projects/recipes/en/latest/Google/Gemma4.html#full-featured-server-launch

command and error message:

$ VLLM_USE_MODELSCOPE=true \
vllm serve RedHatAI/gemma-4-31B-it-FP8_BLOCK \
  --port 8000 \
  --tensor-parallel-size 4 \
  --max-model-len 120000 \
  --reasoning-parser gemma4 \
  --enable-auto-tool-choice \
  --tool-call-parser gemma4 \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.93 \
  --limit-mm-per-prompt image=4,audio=1 \
  --max-num-seqs 1
usage: vllm serve [model_tag] [options]
vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function loads at 0x7a37a144c5e0>.

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

TL;DR

The error occurs due to an invalid value for the --limit-mm-per-prompt argument, which cannot be converted to the expected format.

Guidance

Check the documentation for the correct format of the --limit-mm-per-prompt argument, as the provided value image=4,audio=1 is not valid.
Verify that the --limit-mm-per-prompt argument is used correctly, and consider removing or modifying it if it's not necessary for the command.
Review the command and options used to launch the vllm serve command to ensure they match the documentation and examples provided.
If the issue persists, try searching for similar issues or seeking help from the documentation page's chatbot.

Notes

The provided error message suggests a formatting issue with the --limit-mm-per-prompt argument, but without further information or documentation on this specific argument, it's difficult to provide a more detailed solution.

Recommendation

Apply workaround: Remove or modify the --limit-mm-per-prompt argument to match the expected format, and retry the command. If the issue persists, seek further assistance from the documentation or support resources.

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?

#api #environment variable #container setup #orchestration issue #cache issue

Still need to ship something?

×6

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

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

vllm - ✅(Solved) Fix [Bug]: vllm(g0e39202ca) vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #39802: [Frontend] Improve parse_type error message for JSON dict CLI args

Description (problem / solution / changelog)

Summary

Duplicate check

Test Plan

Changed files

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - ✅(Solved) Fix [Bug]: vllm(g0e39202ca) vllm serve: error: argument --limit-mm-per-prompt: Value image=4,audio=1 cannot be converted to <function [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #39802: [Frontend] Improve parse_type error message for JSON dict CLI args

Description (problem / solution / changelog)

Summary

Duplicate check

Test Plan

Changed files

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING