# horseee/LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA,  BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Repository: https://github.com/horseee/LLM-Pruner
Canonical: https://ross.abutalabs.com/products/llm-pruner
Homepage: https://arxiv.org/abs/2305.11627
Language: Python
License: Apache-2.0
License Family: permissive
Topics: compression, language-model, llm, pruning, pruning-algorithms, baichuan, chatglm, llama, vicuna, llama-2, bloom, neurips-2023, llama3
Last push: 2024-10-07T08:49:26+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 86
- inputs: {"age_days": 1204, "days_push": 695, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1136, forks 132 (observed 2026-08-28T04:03:43.611516+00:00)

## What it is
LLM-Pruner is a PyTorch library implementing structural pruning of large language models based on gradient information, as published at NeurIPS 2023. It compresses models like LLaMA, Llama-2/3, Vicuna, BLOOM, and Baichuan to smaller sizes with fast post-training recovery via LoRA.

## Use cases
- prune a llama model to a smaller size
- compress large language models for cheaper inference
- structurally prune llm weights with gradient-based importance
- recover pruned model quality with lora fine-tuning
- shrink llama-3 or vicuna while keeping multi-task ability

## When to choose
- you need task-agnostic size reduction of a supported LLM family
- you want fast pruning with minimal post-training data (50k samples)
- you are researching structural pruning methods for transformers

## When to avoid
- you need quantization-only compression without structural changes
- your model architecture is not among the supported families
- you need production-grade serving rather than compression research tooling

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, deep-learning
- domain: large-language-models, machine-learning, deep-learning
- platform: python
- tags: model-compression, structural-pruning, llama, lora, neurips-2023, pytorch, gpu

## Member repositories
- horseee/LLM-Pruner (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.611516+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 2026-08-30T06:36:31.039260+00:00, confidence not recorded.
  - readme: https://github.com/horseee/LLM-Pruner (fetched 2026-08-28T04:03:43.611516+00:00, sha 1c7b6c80a948)
  - homepage: https://arxiv.org/abs/2305.11627 (fetched 2026-08-29T12:41:46.743513+00:00, sha 313e78e78ed0)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:41:46.755727+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:41:46.752462+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:41:46.757647+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:41:46.754097+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.