Skip to main content

vLLM plugin for Spyre hardware support

Project description

Spyre Plugin for vLLM

| Documentation | Users Forum | #sig-spyre |


IBM Spyre is the first production-grade Artificial Intelligence Unit (AIU) accelerator born out of the IBM Research AIU family, and is part of a long-term strategy of developing novel architectures and full-stack technology solutions for the emerging space of generative AI. Spyre builds on the foundation of IBM’s internal AIU research and delivers a scalable, efficient architecture for accelerating AI in enterprise environments.

The vLLM Spyre plugin (vllm-spyre) is a dedicated backend extension that enables seamless integration of IBM Spyre Accelerator with vLLM. It follows the architecture described in vLLM's Plugin System, making it easy to integrate IBM's advanced AI acceleration into existing vLLM workflows.

For more information, check out the following:

Getting Started

Visit our documentation:

Contributing

We welcome and value any contributions and collaborations. Please check out Contributing to vLLM Spyre for how to get involved.

Contact

You can reach out for discussion or support in the #sig-spyre channel in the vLLM Slack workspace or by opening an issue.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vllm_spyre-1.4.0.tar.gz (1.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vllm_spyre-1.4.0-py3-none-any.whl (89.9 kB view details)

Uploaded Python 3

File details

Details for the file vllm_spyre-1.4.0.tar.gz.

File metadata

  • Download URL: vllm_spyre-1.4.0.tar.gz
  • Upload date:
  • Size: 1.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for vllm_spyre-1.4.0.tar.gz
Algorithm Hash digest
SHA256 3b3ed74fd3d672f94e704d48f0ba5a28424439ba1621f6e8e7bb9cb9731ce047
MD5 84a864e5ebb9b1b9c10021969029653c
BLAKE2b-256 1a08ec42027524278af4a99ed2632f6d6af37040d1d64f938decb3d373997fc2

See more details on using hashes here.

Provenance

The following attestation bundles were made for vllm_spyre-1.4.0.tar.gz:

Publisher: build_and_publish.yaml on vllm-project/vllm-spyre

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vllm_spyre-1.4.0-py3-none-any.whl.

File metadata

  • Download URL: vllm_spyre-1.4.0-py3-none-any.whl
  • Upload date:
  • Size: 89.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for vllm_spyre-1.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4e39687b3711ae3d13f89c637f783fc67aa57387af17a8d4637812307a6e8f2e
MD5 751459b448424f8c43a41b197b5b8d29
BLAKE2b-256 877b0170124b26f4e03b8bfd950c2c773125559ea062614f807523cec8362473

See more details on using hashes here.

Provenance

The following attestation bundles were made for vllm_spyre-1.4.0-py3-none-any.whl:

Publisher: build_and_publish.yaml on vllm-project/vllm-spyre

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page