vLLM RBLN Plugin

This repository provides the hardware plugin that enables vLLM on RBLN NPUs, including ATOM and REBEL.

Built on top of vLLM’s Plugin System, it allows seamless integration with the vLLM ecosystem and provides high-throughput, low-latency LLM serving on RBLN hardware. Our plugin supports a wide range of popular LLMs and continues to expand to support all features enabled in vLLM, including advanced attention mechanisms.

🚀 Getting Started

📋 Prerequisites

rebel-compiler
optimum-rbln

⚙️ Installation

You can install this project using pip or from source.

Install via PyPI

Using uv

uv pip install vllm-rbln --extra-index-url https://wheels.vllm.ai/0.30.0/cpu --torch-backend cpu

Using pip

pip install vllm-rbln --extra-index-url https://wheels.vllm.ai/0.30.0/cpu --extra-index-url https://download.pytorch.org/whl/cpu

⚠️ Installing on Ubuntu 22.04 or Enterprise Linux 9

If installation fails with an error like the following, use the installation command below:
vllm==0.30.0+cpu has no wheels with a matching platform tag
(e.g., `manylinux_2_35_x86_64`)

hint: Wheels are available for `vllm` (v0.30.0+cpu) on the following platforms:
`manylinux_2_39_aarch64`, `manylinux_2_39_x86_64`
This error means that the upstream vLLM CPU wheel requires a newer glibc version than your system provides. The wheel requires glibc 2.39 or later and libstdc++ from GCC 14 or later (CXXABI_1.3.15). Ubuntu 22.04 (glibc 2.35, GCC 12) and Enterprise Linux 9 (RHEL, AlmaLinux, and Rocky Linux 9.x; glibc 2.34, GCC 11) do not meet these requirements.

The following command uses --find-links to install a compatible vLLM wheel from the vllm-rbln v0.12.0 release assets:
pip3 install \
  --extra-index-url https://wheels.vllm.ai/0.30.0/cpu \
  --extra-index-url https://pypi.rbln.ai/simple \
  --extra-index-url https://download.pytorch.org/whl/cpu \
  --find-links https://github.com/RBLN-SW/vllm-rbln/releases/expanded_assets/v0.12.0 \
  "vllm-rbln[kv-connectors]==0.12.0"

Or from source

Using uv

git clone https://github.com/rbln-sw/vllm-rbln.git
cd vllm-rbln
uv pip install -e .

Using pip

git clone https://github.com/rbln-sw/vllm-rbln.git
cd vllm-rbln
pip install -e . --extra-index-url https://wheels.vllm.ai/0.30.0/cpu --extra-index-url https://download.pytorch.org/whl/cpu

🛠️ Development setup

Building from source? See DEVELOPMENT.md for the uv dev workflow.

📚 Documentation

🤝 Contributing

We welcome all contributions! Whether it's reporting issues, proposing enhancements, or improving docs—your input helps make the project better.

See our CONTRIBUTING.md for more information.

📄 License

This project is licensed under the Apache License 2.0.

See the LICENSE file for more information.

📧 Contact

Join discussions and get answers in our Developer Community
Contact maintainers at support@rebellions.ai

Metadata

Release files for vllm-rbln 0.12.0

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

Built distribution (wheel)

Table of built distributions (wheels) for vllm-rbln 0.12.0
File	Interpreter	ABI	Platform	Reset
vllm_rbln-0.12.0-py3-none-any.whl 648.1 kB Oct 16, 2026	Python 3	none	any	Details

Release files / vllm_rbln-0.12.0-py3-none-any.whl

Download URL	vllm_rbln-0.12.0-py3-none-any.whl
Size	648.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0af77bcf84421b15ffbb9625b880ce2184f6afa4cc720e91dd2c904d19ee2263`
BLAKE2b-256 checksum How to use checksums	`287a8d4ff5403a1e3f10f53808ba8f55c1b8df6f7a0f3dfae374961e7de62de2`
Upload date	Oct 16, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.16`