Metadata-Version: 2.4
Name: llmcompressor
Version: 0.5.1a20250423
Summary: A library for compressing large language models utilizing the latest techniques and research in the field for both training aware and post training techniques. The library is designed to be flexible and easy to use on top of PyTorch and HuggingFace Transformers, allowing for quick experimentation.
Home-page: https://github.com/vllm-project/llm-compressor
Author: Neuralmagic, Inc.
Author-email: support@neuralmagic.com
License: Apache
Keywords: llmcompressor,llms,large language models,transformers,pytorch,huggingface,compressors,compression,quantization,pruning,sparsity,optimization,model optimization,model compression,
Classifier: Development Status :: 5 - Production/Stable
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: POSIX :: Linux
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
License-File: NOTICE
Requires-Dist: loguru
Requires-Dist: pyyaml>=5.0.0
Requires-Dist: numpy<2.0,>=1.17.0
Requires-Dist: requests>=2.0.0
Requires-Dist: tqdm>=4.0.0
Requires-Dist: torch>=1.7.0
Requires-Dist: transformers<5.0,>4.0
Requires-Dist: datasets
Requires-Dist: accelerate!=1.1.0,>=0.20.3
Requires-Dist: pynvml
Requires-Dist: pillow
Requires-Dist: compressed-tensors>=0.9.4a2
Provides-Extra: dev
Requires-Dist: pytest>=6.0.0; extra == "dev"
Requires-Dist: pytest-mock>=3.6.0; extra == "dev"
Requires-Dist: pytest-rerunfailures>=13.0; extra == "dev"
Requires-Dist: parameterized; extra == "dev"
Requires-Dist: lm_eval==0.4.5; extra == "dev"
Requires-Dist: beautifulsoup4~=4.12.3; extra == "dev"
Requires-Dist: cmarkgfm~=2024.1.14; extra == "dev"
Requires-Dist: trl>=0.10.1; extra == "dev"
Requires-Dist: pandas; extra == "dev"
Requires-Dist: black~=24.4.2; extra == "dev"
Requires-Dist: isort~=5.13.2; extra == "dev"
Requires-Dist: mypy~=1.10.0; extra == "dev"
Requires-Dist: ruff~=0.4.8; extra == "dev"
Requires-Dist: flake8~=7.0.0; extra == "dev"
Requires-Dist: pre-commit; extra == "dev"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# <img width="40" alt="tool icon" src="https://github.com/user-attachments/assets/f9b86465-aefa-4625-a09b-54e158efcf96" />  LLM Compressor
`llmcompressor` is an easy-to-use library for optimizing models for deployment with `vllm`, including:

* Comprehensive set of quantization algorithms for weight-only and activation quantization
* Seamless integration with Hugging Face models and repositories
* `safetensors`-based file format compatible with `vllm`
* Large model support via `accelerate`

**✨ Read the announcement blog [here](https://neuralmagic.com/blog/llm-compressor-is-here-faster-inference-with-vllm/)! ✨**

<p align="center">
   <img alt="LLM Compressor Flow" src="https://github.com/user-attachments/assets/adf07594-6487-48ae-af62-d9555046d51b" width="80%" />
</p>

### Supported Formats
* Activation Quantization: W8A8 (int8 and fp8)
* Mixed Precision: W4A16, W8A16
* 2:4 Semi-structured and Unstructured Sparsity

### Supported Algorithms
* Simple PTQ
* GPTQ
* AWQ
* SmoothQuant
* SparseGPT

### When to Use Which Optimization

Please refer to [docs/schemes.md](./docs/schemes.md) for detailed information about available optimization schemes and their use cases.


## Installation

```bash
pip install llmcompressor
```

## Get Started

### End-to-End Examples

Applying quantization with `llmcompressor`:
* [Activation quantization to `int8`](examples/quantization_w8a8_int8/README.md)
* [Activation quantization to `fp8`](examples/quantization_w8a8_fp8/README.md)
* [Weight only quantization to `int4` using GPTQ](examples/quantization_w4a16/README.md)
* [Weight only quantization to `int4` using AWQ](examples/awq/awq_one_shot.py)
* [Quantizing MoE LLMs](examples/quantizing_moe/README.md)
* [Quantizing Vision-Language Models](examples/multimodal_vision/README.md)
* [Quantizing Audio-Language Models](examples/multimodal_audio/README.md)

### User Guides
Deep dives into advanced usage of `llmcompressor`:
* [Quantizing with large models with the help of `accelerate`](examples/big_models_with_accelerate/README.md)


## Quick Tour
Let's quantize `TinyLlama` with 8 bit weights and activations using the `GPTQ` and `SmoothQuant` algorithms.

Note that the model can be swapped for a local or remote HF-compatible checkpoint and the `recipe` may be changed to target different quantization algorithms or formats.

### Apply Quantization
Quantization is applied by selecting an algorithm and calling the `oneshot` API.

```python
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor import oneshot

# Select quantization algorithm. In this case, we:
#   * apply SmoothQuant to make the activations easier to quantize
#   * quantize the weights to int8 with GPTQ (static per channel)
#   * quantize the activations to int8 (dynamic per token)
recipe = [
    SmoothQuantModifier(smoothing_strength=0.8),
    GPTQModifier(scheme="W8A8", targets="Linear", ignore=["lm_head"]),
]

# Apply quantization using the built in open_platypus dataset.
#   * See examples for demos showing how to pass a custom calibration set
oneshot(
    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
    dataset="open_platypus",
    recipe=recipe,
    output_dir="TinyLlama-1.1B-Chat-v1.0-INT8",
    max_seq_length=2048,
    num_calibration_samples=512,
)
```

### Inference with vLLM

The checkpoints created by `llmcompressor` can be loaded and run in `vllm`:

Install:

```bash
pip install vllm
```

Run:

```python
from vllm import LLM
model = LLM("TinyLlama-1.1B-Chat-v1.0-INT8")
output = model.generate("My name is")
```

## Questions / Contribution

- If you have any questions or requests open an [issue](https://github.com/vllm-project/llm-compressor/issues) and we will add an example or documentation.
- We appreciate contributions to the code, examples, integrations, and documentation as well as bug reports and feature requests! [Learn how here](CONTRIBUTING.md).
