vllm-bnb-plugin
Out-of-tree bitsandbytes quantization plugin for vLLM.
Install
uv pip install -e /path/to/vllm-bnb-plugin
The package registers itself through the vllm.general_plugins entry-point
group, so quantization="bitsandbytes" and load_format="bitsandbytes"
remain available after installation.
What it provides
- in-flight 4-bit bitsandbytes quantization
- pre-quantized 4-bit and 8-bit bitsandbytes checkpoint loading
- bitsandbytes linear and MoE quantization methods
Development
Install and enable the lint hooks:
uv pip install -r requirements/lint.txt
pre-commit install
Run all hooks:
pre-commit run --all-files
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vllm_bnb_plugin-0.0.1.tar.gz.
File metadata
- Download URL: vllm_bnb_plugin-0.0.1.tar.gz
- Upload date:
- Size: 23.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
64be2ecba1af20478e273c01c70c4f6bee2a787c10d312cc465f8b7c591db6ed
|
|
| MD5 |
b84145cdde43db8e1069fb1148bbceda
|
|
| BLAKE2b-256 |
bc9a7292c4af04bb34d63a78a0f5e76179621f3537caa66bdbf98aea6d9bba2f
|
Provenance
The following attestation bundles were made for vllm_bnb_plugin-0.0.1.tar.gz:
Publisher:
release.yml on vllm-project/vllm-bnb-plugin
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
vllm_bnb_plugin-0.0.1.tar.gz -
Subject digest:
64be2ecba1af20478e273c01c70c4f6bee2a787c10d312cc465f8b7c591db6ed - Sigstore transparency entry: 2288656418
- Sigstore integration time:
-
Permalink:
vllm-project/vllm-bnb-plugin@8fdc1db02644a67eb8cd1c79d757286a66a34d36 -
Branch / Tag:
refs/tags/v0.0.1 - Owner: https://github.com/vllm-project
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@8fdc1db02644a67eb8cd1c79d757286a66a34d36 -
Trigger Event:
release
-
Statement type:
File details
Details for the file vllm_bnb_plugin-0.0.1-py3-none-any.whl.
File metadata
- Download URL: vllm_bnb_plugin-0.0.1-py3-none-any.whl
- Upload date:
- Size: 23.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cf19ea5a7211ab8c4b43c14bb2e42a5d23eea3722fc8869e368adf8c112a1406
|
|
| MD5 |
151c2f8be8ef81261edad54e3508921c
|
|
| BLAKE2b-256 |
6a8c4c3df35e0067e7316e2b65df96a5c3b243127ed297f3e851f20b1b2de22e
|
Provenance
The following attestation bundles were made for vllm_bnb_plugin-0.0.1-py3-none-any.whl:
Publisher:
release.yml on vllm-project/vllm-bnb-plugin
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
vllm_bnb_plugin-0.0.1-py3-none-any.whl -
Subject digest:
cf19ea5a7211ab8c4b43c14bb2e42a5d23eea3722fc8869e368adf8c112a1406 - Sigstore transparency entry: 2288656443
- Sigstore integration time:
-
Permalink:
vllm-project/vllm-bnb-plugin@8fdc1db02644a67eb8cd1c79d757286a66a34d36 -
Branch / Tag:
refs/tags/v0.0.1 - Owner: https://github.com/vllm-project
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@8fdc1db02644a67eb8cd1c79d757286a66a34d36 -
Trigger Event:
release
-
Statement type:
