DGX Spark vLLM

Pre-built vLLM environment for NVIDIA DGX Spark (GB10, sm_121).

About

This package contains the vLLM environment extracted from NVIDIA's official nvcr.io/nvidia/vllm:25.09-py3 Docker image, configured for local installation on DGX Spark without Docker.

Why? The official vLLM doesn't support sm_121 (GB10) yet. NVIDIA's Docker image has patches for Blackwell support, but requires running everything in a container. This package lets you run vLLM natively on DGX Spark.

Requirements

NVIDIA DGX Spark (GB10 chip, sm_121)
Ubuntu with CUDA 13.0 installed
Python 3.12
aarch64 (ARM64) architecture

Installation

pip install dgx-spark-vllm
sudo dgx-spark-vllm-install

Then restart your shell or run:

source /etc/profile.d/nvidia-venv.sh

Included Versions

Package	Version
PyTorch	2.9.0a0+50eac811a6.nv25.09
vLLM	0.10.1.1+381074ae.nv25.09
CUDA	13.0
Triton	3.4.0
FlashAttention	2.7.4
cuDNN	9.13.0
NCCL	2.27.7

Usage

import torch
print(torch.__version__)  # 2.9.0a0+50eac811a6.nv25.09
print(torch.cuda.get_device_name(0))  # NVIDIA GB10

import vllm
print(vllm.__version__)  # 0.10.1.1+381074ae.nv25.09

Run vLLM server:

python3 -m vllm.entrypoints.openai.api_server --model <model_name>

What's Installed

/home/srpost/shared/nvidia-venv/ - Python packages
/opt/hpcx/ - HPC-X libraries (UCX, UCC, OpenMPI)
/usr/lib/aarch64-linux-gnu/libcudnn* - cuDNN
/usr/lib/aarch64-linux-gnu/libnccl* - NCCL
/usr/local/lib/libnvpl* - NVPL (NVIDIA Performance Libraries)
/etc/ld.so.conf.d/00-hpcx.conf - Library path config
/etc/profile.d/nvidia-venv.sh - PYTHONPATH config

License

The installer is Apache 2.0. The installed packages retain their original licenses (PyTorch BSD, vLLM Apache 2.0, NVIDIA components under NVIDIA license).

Metadata

Release files for dgx-spark-vllm 25.9.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dgx-spark-vllm 25.9.3
File	Size	Uploaded	Provenance
dgx_spark_vllm-25.9.3.tar.gz	4.0 kB	Dec 11, 2025	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for dgx-spark-vllm 25.9.3
File	Interpreter	ABI	Platform	Reset
dgx_spark_vllm-25.9.3-py3-none-any.whl 4.5 kB Dec 11, 2025 Without provenance	Python 3	none	any	Details

Total release size: 8.5 kB

Release files / dgx_spark_vllm-25.9.3.tar.gz

Download URL	dgx_spark_vllm-25.9.3.tar.gz
Size	4.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`0b2922d9d8ac1e1d137111e41d2ac0e18d774908c254fb0bc2df89af8ca4ec74`
BLAKE2b-256 checksum How to use checksums	`355521ecdbf58caba8dd1b9e5c6022bb8b4d2591b8012967301913a40b5a7302`
Upload date	Dec 11, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.12.3`

Release files / dgx_spark_vllm-25.9.3-py3-none-any.whl

Download URL	dgx_spark_vllm-25.9.3-py3-none-any.whl
Size	4.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`ced810431d614cb5d7c2b400d5c828738921d12e97e68bf71ff054bdb1055409`
BLAKE2b-256 checksum How to use checksums	`793022280f944b896d7fc95fc0915f436019229a6e07a2bcd8242d3dabe3a429`
Upload date	Dec 11, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.12.3`

Security for dgx-spark-vllm 25.9.3

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.