vllm - 💡(How to fix) Fix [Usage]: v0.18.0 nvidia/nemotron-colembed-vl-4b-v2 /embeddings 404 [2 comments, 2 participants]

vllm2026-03-23 20:50:50

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#37928•Fetched 2026-04-08 01:22:39

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Participants

Assignees

Timeline (top)

commented ×2assigned ×1labeled ×1mentioned ×1

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): 64 On-line CPU(s) list: 0-63 Vendor ID: AuthenticAMD Model name: AMD EPYC 7543P 32-Core Processor CPU family: 25 Model: 1 Thread(s) per core: 2 Core(s) per socket: 32 Socket(s): 1 Stepping: 1 BogoMIPS: 5589.57 Flags: Virtualization: AMD-V L1d cache: 1 MiB (32 instances) L1i cache: 1 MiB (32 instances) L2 cache: 16 MiB (32 instances) L3 cache: 256 MiB (8 instances) NUMA node(s): 4 NUMA node0 CPU(s): 0-7,32-39 NUMA node1 CPU(s): 8-15,40-47 NUMA node2 CPU(s): 16-23,48-55 NUMA node3 CPU(s): 24-31,56-63 Vulnerability Gather data sampling: 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 Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

Code Example

$ python3 collect_env.py
Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar  4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime)
Python platform              : Linux-4.18.0-553.97.1.el8_10.x86_64-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : Could not collect
Nvidia driver version        : Could not collect
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):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7543P 32-Core Processor
CPU family:                           25
Model:                                1
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            1
Stepping:                             1
BogoMIPS:                             5589.57
Flags:
Virtualization:                       AMD-V
L1d cache:                            1 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             16 MiB (32 instances)
L3 cache:                             256 MiB (8 instances)
NUMA node(s):                         4
NUMA node0 CPU(s):                    0-7,32-39
NUMA node1 CPU(s):                    8-15,40-47
NUMA node2 CPU(s):                    16-23,48-55
NUMA node3 CPU(s):                    24-31,56-63
Vulnerability Gather data sampling:   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 Tsx async abort:        Not affected
Vulnerability Vmscape:                Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[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-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu129
[pip3] torchvision==0.25.0+cu129
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.0
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
  Could not collect


==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571
TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.9 9.0 10.0 12.0
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/.singularity.d/libs
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

---

vllm serve nvidia/nemotron-colembed-vl-4b-v2 \
    --max-model-len 10240 \
    --runner pooling \
    --host 0.0.0.0

(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]        █     █     █▄   ▄█
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.18.0
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]   █▄█▀ █     █     █     █  model  nvidia/nemotron-colembed-vl-4b-v2
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:233] non-default args: {'model_tag': 'nvidia/nemotron-colembed-vl-4b-v2', 'host': '0.0.0.0', 'port': 42003, 'model': 'nvidia/nemotron-colembed-vl-4b-v2', 'runner': 'pooling', 'max_model_len': 10240, 'se
rved_model_name': ['nemotron-colembed-vl-4b-v2']}
(APIServer pid=2503732) Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'rope_theta'}
(APIServer pid=2503732) INFO 03-23 14:45:36 [model.py:533] Resolved architecture: Qwen3VLNemotronEmbedMode
l
(APIServer pid=2503732) INFO 03-23 14:45:36 [model.py:1582] Using max model len 10240
(APIServer pid=2503732) INFO 03-23 14:45:36 [vllm.py:754] Asynchronous scheduling is enabled.
(APIServer pid=2503732) WARNING 03-23 14:45:36 [vllm.py:916] Pooling models do not support full cudagraphs
. Overriding cudagraph_mode to PIECEWISE.
...
(EngineCore pid=2503961) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
Loading safetensors checkpoint shards:   0% Completed | 0/2 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 100% Completed | 2/2 [00:00<00:00, 103.98it/s]
(EngineCore pid=2503961)
(EngineCore pid=2503961) INFO 03-23 14:46:00 [default_loader.py:384] Loading weights took 1.14 seconds
(EngineCore pid=2503961) INFO 03-23 14:46:00 [gpu_model_runner.py:4566] Model loading took 8.71 GiB memory and 2.546249 seconds
...
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|████████████| 51/51 [00:01<00:00, 27.73it/s]
(EngineCore pid=2503961) INFO 03-23 14:46:12 [gpu_model_runner.py:5746] Graph capturing finished in 2 secs, took 0.39 GiB
(EngineCore pid=2503961) INFO 03-23 14:46:12 [gpu_worker.py:617] CUDA graph pool memory: 0.39 GiB (actual), 0.38 GiB (estimated), difference: 0.01 GiB (2.0%).
(EngineCore pid=2503961) INFO 03-23 14:46:12 [core.py:281] init engine (profile, create kv cache, warmup model) took 11.24 seconds
(APIServer pid=2503732) INFO 03-23 14:46:12 [api_server.py:576] Supported tasks: ['token_embed']
(APIServer pid=2503732) WARNING 03-23 14:46:12 [utils.py:140] To make v1/embeddings API fast, please install orjson by `pip install orjson`
(APIServer pid=2503732) INFO 03-23 14:46:12 [api_server.py:580] Starting vLLM server on http://0.0.0.0:42003
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:37] Available routes are:
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /docs, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /pooling, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /score, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/score, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /rerank, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/rerank, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=2503732) INFO:     Started server process [2503732]
(APIServer pid=2503732) INFO:     Waiting for application startup.
(APIServer pid=2503732) INFO:     Application startup complete.
(APIServer pid=2503732) INFO:     10.48.16.3:36314 - "POST /embeddings HTTP/1.1" 404 Not Found

RAW_BUFFERClick to expand / collapse

Your current environment

$ python3 collect_env.py
Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar  4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime)
Python platform              : Linux-4.18.0-553.97.1.el8_10.x86_64-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : Could not collect
Nvidia driver version        : Could not collect
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):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7543P 32-Core Processor
CPU family:                           25
Model:                                1
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            1
Stepping:                             1
BogoMIPS:                             5589.57
Flags:
Virtualization:                       AMD-V
L1d cache:                            1 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             16 MiB (32 instances)
L3 cache:                             256 MiB (8 instances)
NUMA node(s):                         4
NUMA node0 CPU(s):                    0-7,32-39
NUMA node1 CPU(s):                    8-15,40-47
NUMA node2 CPU(s):                    16-23,48-55
NUMA node3 CPU(s):                    24-31,56-63
Vulnerability Gather data sampling:   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 Tsx async abort:        Not affected
Vulnerability Vmscape:                Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[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-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu129
[pip3] torchvision==0.25.0+cu129
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.0
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
  Could not collect


==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571
TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.9 9.0 10.0 12.0
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/.singularity.d/libs
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

How would you like to use vllm

I want to utilize the embedding model https://huggingface.co/nvidia/nemotron-colembed-vl-4b-v2. I can start the model, but there's no /embedding endpoint. The /pooling endpoint works, but it isn't compatible with the Python OpenAI sdk

I'm utilizing the latest vllm v0.18.0 dockerhub container.

vllm serve nvidia/nemotron-colembed-vl-4b-v2 \
    --max-model-len 10240 \
    --runner pooling \
    --host 0.0.0.0

(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]        █     █     █▄   ▄█
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.18.0
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]   █▄█▀ █     █     █     █  model  nvidia/nemotron-colembed-vl-4b-v2
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:297]
(APIServer pid=2503732) INFO 03-23 14:45:36 [utils.py:233] non-default args: {'model_tag': 'nvidia/nemotron-colembed-vl-4b-v2', 'host': '0.0.0.0', 'port': 42003, 'model': 'nvidia/nemotron-colembed-vl-4b-v2', 'runner': 'pooling', 'max_model_len': 10240, 'se
rved_model_name': ['nemotron-colembed-vl-4b-v2']}
(APIServer pid=2503732) Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'rope_theta'}
(APIServer pid=2503732) INFO 03-23 14:45:36 [model.py:533] Resolved architecture: Qwen3VLNemotronEmbedMode
l
(APIServer pid=2503732) INFO 03-23 14:45:36 [model.py:1582] Using max model len 10240
(APIServer pid=2503732) INFO 03-23 14:45:36 [vllm.py:754] Asynchronous scheduling is enabled.
(APIServer pid=2503732) WARNING 03-23 14:45:36 [vllm.py:916] Pooling models do not support full cudagraphs
. Overriding cudagraph_mode to PIECEWISE.
...
(EngineCore pid=2503961) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
Loading safetensors checkpoint shards:   0% Completed | 0/2 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 100% Completed | 2/2 [00:00<00:00, 103.98it/s]
(EngineCore pid=2503961)
(EngineCore pid=2503961) INFO 03-23 14:46:00 [default_loader.py:384] Loading weights took 1.14 seconds
(EngineCore pid=2503961) INFO 03-23 14:46:00 [gpu_model_runner.py:4566] Model loading took 8.71 GiB memory and 2.546249 seconds
...
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|████████████| 51/51 [00:01<00:00, 27.73it/s]
(EngineCore pid=2503961) INFO 03-23 14:46:12 [gpu_model_runner.py:5746] Graph capturing finished in 2 secs, took 0.39 GiB
(EngineCore pid=2503961) INFO 03-23 14:46:12 [gpu_worker.py:617] CUDA graph pool memory: 0.39 GiB (actual), 0.38 GiB (estimated), difference: 0.01 GiB (2.0%).
(EngineCore pid=2503961) INFO 03-23 14:46:12 [core.py:281] init engine (profile, create kv cache, warmup model) took 11.24 seconds
(APIServer pid=2503732) INFO 03-23 14:46:12 [api_server.py:576] Supported tasks: ['token_embed']
(APIServer pid=2503732) WARNING 03-23 14:46:12 [utils.py:140] To make v1/embeddings API fast, please install orjson by `pip install orjson`
(APIServer pid=2503732) INFO 03-23 14:46:12 [api_server.py:580] Starting vLLM server on http://0.0.0.0:42003
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:37] Available routes are:
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /docs, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /pooling, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /score, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/score, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /rerank, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v1/rerank, Methods: POST
(APIServer pid=2503732) INFO 03-23 14:46:12 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=2503732) INFO:     Started server process [2503732]
(APIServer pid=2503732) INFO:     Waiting for application startup.
(APIServer pid=2503732) INFO:     Application startup complete.
(APIServer pid=2503732) INFO:     10.48.16.3:36314 - "POST /embeddings HTTP/1.1" 404 Not Found

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

To fix the issue of the missing /embedding endpoint, you need to use the --runner embedding flag instead of --runner pooling when serving the model. Here are the steps:

Stop the current vLLM server process.
Run the following command to serve the model with the embedding runner:

vllm serve nvidia/nemotron-colembed-vl-4b-v2 \
    --max-model-len 10240 \
    --runner embedding \
    --host 0.0.0.0

This will start the vLLM server with the embedding endpoint enabled.

Verification

To verify that the fix worked, you can check the available routes by looking at the server logs or by using a tool like curl to query the /openapi.json endpoint:

curl http://0.0.0.0:42003/openapi.json

This should return a JSON response that includes the /embeddings endpoint.

You can also test the /embeddings endpoint directly using a tool like curl:

curl -X POST \
  http://0.0.0.0:42003/embeddings \
  -H 'Content-Type: application/json' \
  -d '{"input": "Your input text here"}'

This should return a JSON response with the embedding results.

Extra Tips

Make sure to check the vLLM documentation for the latest information on available runners and endpoints. Additionally, you can use the --help flag to see the available options and flags for the vllm serve command.

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 #model loading #environment variable #network issue #logging 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 - 💡(How to fix) Fix [Usage]: v0.18.0 nvidia/nemotron-colembed-vl-4b-v2 /embeddings 404 [2 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

How would you like to use vllm

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Usage]: v0.18.0 nvidia/nemotron-colembed-vl-4b-v2 /embeddings 404 [2 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

How would you like to use vllm

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING