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-1.5.0.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-1.5.0-py3-none-any.whl (92.3 kB view details)

Uploaded Python 3

File details

Details for the file vllm_spyre-1.5.0.tar.gz.

File metadata

  • Download URL: vllm_spyre-1.5.0.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-1.5.0.tar.gz
Algorithm Hash digest
SHA256 307f0661774a003faad0b8617d0e8ed6d655793c94efdcb14b6caa02ac5b3151
MD5 42bf66732cada0908a8308e47320a043
BLAKE2b-256 d26b2273998623b1b82daee0c9c71cea4165d543904dfacf6575a4a07f458656

See more details on using hashes here.

Provenance

The following attestation bundles were made for vllm_spyre-1.5.0.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-1.5.0-py3-none-any.whl.

File metadata

  • Download URL: vllm_spyre-1.5.0-py3-none-any.whl
  • Upload date:
  • Size: 92.3 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-1.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 44c732cbe297f0ae772666438375ce87bddc2f3c7a24f949932e19c64e6bb36c
MD5 7a5182840ca71b19b70441796e33870a
BLAKE2b-256 b888cdcc6f55c0778145e9e25e01e6204cdbae231737b6fa425c5cad77d61f1b

See more details on using hashes here.

Provenance

The following attestation bundles were made for vllm_spyre-1.5.0-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