# vllm-project/llm-compressor

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Repository: https://github.com/vllm-project/llm-compressor
Canonical: https://ross.abutalabs.com/products/llm-compressor
Homepage: https://docs.vllm.ai/projects/llm-compressor
Language: Python
License: Apache-2.0
License Family: permissive
Topics: compression, quantization
Last push: 2026-08-26T22:26:14+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 57
- inputs: {"age_days": 804, "days_push": 7, "days_rel": 22, "gap_med": 23.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3726, forks 637 (observed 2026-08-28T04:08:15.663534+00:00)

## What it is
LLM Compressor is a Python library for applying quantization and pruning algorithms to large language models, producing compressed-tensors checkpoints optimized for vLLM deployment. It integrates with Hugging Face Transformers and supports weight, activation, KV cache, and attention quantization including MoE expert pruning.

## Use cases
- quantize an LLM to fp8 or int4 for vLLM inference
- reduce GPU memory requirements for serving large language models
- compress a Hugging Face model into compressed-tensors format
- prune experts from a mixture-of-experts model
- speed up LLM inference with lower-precision weights

## When to choose
- you deploy models with vLLM and want smaller, faster checkpoints
- you need state-of-the-art quantization schemes like NVFP4, FP8, or arbitrary bit-widths
- you work with Hugging Face Transformers models and want a pip-installable optimization pipeline

## When to avoid
- you expect faster inference through plain transformers - compressed models only accelerate in vLLM or compatible servers
- you need a serving engine itself rather than a model compression tool
- you require SGLang support, which is minimally maintained

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, compression, serialization
- domain: large-language-models, machine-learning, deep-learning, gpu-computing
- platform: python, cross-platform
- tags: quantization, model-optimization, vllm, compressed-tensors, hugging-face, moe, pruning, fp8, int4, linux, gpu

## Member repositories
- vllm-project/llm-compressor (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.663534+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:29:15.664794+00:00, confidence not recorded.
  - readme: https://github.com/vllm-project/llm-compressor (fetched 2026-08-28T04:08:15.663534+00:00, sha dfc04828c70a)
  - homepage: https://docs.vllm.ai/projects/llm-compressor (fetched 2026-08-29T09:23:53.532677+00:00, sha af790c8b7937)
  - site_page: https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started (fetched 2026-08-29T09:23:53.535623+00:00, sha 563d18d8696d)
  - site_page: https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install (fetched 2026-08-29T09:23:53.537588+00:00, sha 325a3fd81fbe)
  - site_page: https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq (fetched 2026-08-29T09:23:53.539461+00:00, sha 56a03c6d3d74)
- Data as of 2026-08-30T08:39:29.467469+00:00.