[Bug]: vllm: error: unrecognized arguments: --config

[FloWsnr]

Hi guys,

I cannot serve an vllm server with a config.yaml file using
vllm serve model --config config.yaml

Regardsless of the specified path, I always get:
vllm: error: unrecognized arguments: --config

I tried quoting the path, I tried relative and absolute path and I also tried a wrong non-existing path. All with the error above.
The server runs just fine if I do not use the --config argument. The content of the .yaml file is just as in the documentation

host: "127.0.0.1"
port: 6379
uvicorn-log-level: "info"

Any idea whats wrong here?

Update:

I tried to manually specify various command and got confusing results.

These work:

vllm serve "/hpcwork/fw641779/llm/Meta-Llama-3.1-8B-Instruct"  --port 6379
vllm serve "/hpcwork/fw641779/llm/Meta-Llama-3.1-8B-Instruct" --uvicorn-log-level info

However, if I start the server via a python subprocess with

main_command = ["vllm", "serve", f"{model_path}", "--host 127.0.0.1", "--port 6379"]
server_p = subprocess.run(main_command)

the commands host and port are suddently unknown.
Again, the server works just fine if no arguments are given.

Update 2:

The python commands work if we use = to assign the arguments:

main_command = ["vllm", "serve", f"{model_path}", "--host=127.0.0.1", "--port=6379"]
server_p = subprocess.run(main_command)

Your current environment

PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Rocky Linux release 8.10 (Green Obsidian) (x86_64)
GCC version: (GCC) 11.3.0
Clang version: Could not collect
CMake version: version 3.26.5
Libc version: glibc-2.28

Python version: 3.11.5 (main, Sep 11 2023, 13:54:46) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-4.18.0-553.16.1.el8_10.x86_64-x86_64-with-glibc2.28
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA H100
GPU 1: NVIDIA H100
GPU 2: NVIDIA H100
  MIG 1g.12gb     Device  0:
  MIG 1g.12gb     Device  1:
  MIG 1g.12gb     Device  2:
  MIG 1g.12gb     Device  3:
  MIG 1g.12gb     Device  4:
  MIG 1g.12gb     Device  5:
  MIG 1g.12gb     Device  6:
GPU 3: NVIDIA H100

Nvidia driver version: 550.90.07
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              96
On-line CPU(s) list: 0-95
Thread(s) per core:  1
Core(s) per socket:  48
Socket(s):           2
NUMA node(s):        8
Vendor ID:           GenuineIntel
CPU family:          6
Model:               143
Model name:          Intel(R) Xeon(R) Platinum 8468
Stepping:            8
CPU MHz:             2100.000
CPU max MHz:         3800.0000
CPU min MHz:         800.0000
BogoMIPS:            4200.00
L1d cache:           48K
L1i cache:           32K
L2 cache:            2048K
L3 cache:            107520K
NUMA node0 CPU(s):   0-11
NUMA node1 CPU(s):   12-23
NUMA node2 CPU(s):   24-35
NUMA node3 CPU(s):   36-47
NUMA node4 CPU(s):   48-59
NUMA node5 CPU(s):   60-71
NUMA node6 CPU(s):   72-83
NUMA node7 CPU(s):   84-95
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 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 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.68
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.0
[pip3] sentence-transformers==3.0.1
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.2
[pip3] triton==3.0.0
[conda] No relevant packages
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.5@09c7792610ada9f88bbf87d32b472dd44bf23cc2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    CPU Affinity    NUMA Affinity      GPU NUMA ID
GPU0     X      NV6     NV6     NV6     SYS     SYS     0-11    0 N/A
GPU1    NV6      X      NV6     NV6     PIX     SYS     24-35   2 N/A
GPU2    SYS     SYS      X      SYS     SYS     SYS     48-59   4 N/A
GPU3    NV6     NV6     NV6      X      SYS     PIX     72-83   6 N/A
NIC0    SYS     PIX     SYS     SYS      X      SYS
NIC1    SYS     SYS     SYS     PIX     SYS      X 

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

NIC Legend:

  NIC0: mlx5_0
  NIC1: mlx5_1

🐛 Describe the bug

vllm serve "/hpcwork/fw641779/llm/Meta-Llama-3.1-8B-Instruct" --config "/home/fw641779/Coding/proposal-mining/mining/server_config.yaml"
usage: vllm [-h] {serve,complete,chat} ...
vllm: error: unrecognized arguments: --config /home/fw641779/Coding/proposal-mining/mining/server_config.yaml

Or similar:

vllm serve /hpcwork/fw641779/llm/Meta-Llama-3.1-8B-Instruct --config ./mining/server_config.yaml 
usage: vllm [-h] {serve,complete,chat} ...
vllm: error: unrecognized arguments: --config ./mining/server_config.yaml

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.

[robertgshaw2-redhat]

Hey - is there an example somewhere that suggests we support loading from a config.yaml?

I dont believe we currently support this. I do think launching with a config.yaml is a great idea though!

[FloWsnr]

I think this option should already be supported:
https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#config-file

You can also see this option in the script code here:
https://github.com/vllm-project/vllm/blob/main/vllm/scripts.py#L128

[robertgshaw2-redhat]

Oh cool! Looks like this just got added

[youkaichao]

vLLM Version: 0.5.5@09c7792610ada9f88bbf87d32b472dd44bf23cc2

#7737 is not released yet. if you want to use it, please use the per-commit wheel. see https://docs.vllm.ai/en/latest/getting_started/installation.html

[robertgshaw2-redhat]

I think this is is v0.6.0

[FloWsnr]

Aah, this explains a lot! Alright, thank you for the fast help! 👍
Closing the issue!