Skip to main content

hs_connectors

hs_connectors is a lightweight package that enables the transfer of hidden states between vLLM and Speculators training processes during both online and offline training. It provides a pluggable backend system where each backend registers itself via @HiddenStatesBackend.register(name) and exposes hooks for CLI argument injection and configuration, so that training and serving scripts can discover and configure backends without hardcoding.

The package should be installed alongside Speculators as well as within the same environment as vLLM.

Backends

Filesystem

The filesystem backend enables the transfer of hidden states between vLLM and Speculators on a single node with a shared filesystem. Hidden states are serialized as safetensors files with file-lock synchronization to prevent partial reads. Cached samples are stored by index and can be reused across training runs.

Mooncake

The Mooncake backend enables multi-node training by transferring hidden states between vLLM and Speculators across nodes over TCP or RDMA, without requiring a shared filesystem. It uses a Mooncake distributed key-value store where each sample is written under a sanitized request ID, with a metadata marker written last to signal that the sample is complete and ready for consumption. This follows a similar pattern to disaggregated prefill and decode.

When using this backend, install the Mooncake transfer engine separately (pip install mooncake-transfer-engine).

Download files

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

Source Distribution

hs_connectors-0.8.0.tar.gz (18.0 kB view details)

Uploaded Source

Built Distribution

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

hs_connectors-0.8.0-py3-none-any.whl (18.0 kB view details)

Uploaded Python 3

File details

Details for the file hs_connectors-0.8.0.tar.gz.

File metadata

  • Download URL: hs_connectors-0.8.0.tar.gz
  • Upload date:
  • Size: 18.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for hs_connectors-0.8.0.tar.gz
Algorithm Hash digest
SHA256 07fcb1b6d0ea2014f9c7f12cffcd67338954d0552a44a2dfb54a833c37722c5e
MD5 855c80da0261d6e7d75d90deb8dc03f2
BLAKE2b-256 3ed86038076ae53a9637e2f8644f65a80758cf9811458bf2e1d5da51f91f6555

See more details on using hashes here.

Provenance

The following attestation bundles were made for hs_connectors-0.8.0.tar.gz:

Publisher: hsc-upload.yml on neuralmagic/llm-compressor-testing

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

File details

Details for the file hs_connectors-0.8.0-py3-none-any.whl.

File metadata

  • Download URL: hs_connectors-0.8.0-py3-none-any.whl
  • Upload date:
  • Size: 18.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for hs_connectors-0.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c2c7826b9f02e5701ee7d3215a9583fc5a19fd38ce7b42383d224f32868052ca
MD5 a0800526e66d643eb51511e8debe903b
BLAKE2b-256 2e244ab4664408e11544681fb114ef5b7248b11dc6458d998aa4c0526aceffc6

See more details on using hashes here.

Provenance

The following attestation bundles were made for hs_connectors-0.8.0-py3-none-any.whl:

Publisher: hsc-upload.yml on neuralmagic/llm-compressor-testing

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

Release history Release notifications | RSS feed

This release

0.8.0 This release

2 files

0.7.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page