This release is a pre-release and may not be stable for production use.
compressed-tensors
The compressed-tensors library extends the safetensors format, providing a versatile and efficient way to store and manage compressed tensor data. This library supports various quantization and sparsity schemes, making it a unified format for handling different model optimizations like GPTQ, AWQ, SmoothQuant, INT8, FP8, SparseGPT, and more.
Why compressed-tensors?
As model compression becomes increasingly important for efficient deployment of LLMs, the landscape of quantization and compression techniques has become increasingly fragmented.
Each method often comes with its own storage format and loading procedures, making it challenging to work with multiple techniques or switch between them.
compressed-tensors addresses this by providing a single, extensible format that can represent a wide variety of compression schemes.
- Unified Checkpoint Format: Supports various compression schemes in a single, consistent format.
- Wide Compatibility: Works with popular quantization methods like GPTQ, SmoothQuant, and FP8. See llm-compressor
- Flexible Quantization Support:
- Weight-only quantization (e.g., W4A16, W8A16, WnA16)
- Activation quantization (e.g., W8A8)
- KV cache quantization
- Non-uniform schemes (different layers can be quantized in different ways!)
- Sparsity Support: Handles both unstructured and semi-structured (e.g., 2:4) sparsity patterns.
- Open-Source Integration: Designed to work seamlessly with Hugging Face models and PyTorch.
This allows developers and researchers to easily experiment with composing different quantization methods, simplify model deployment pipelines, and reduce the overhead of supporting multiple compression formats in inference engines.
Installation
From PyPI
Stable release:
pip install compressed-tensors
Nightly release:
pip install --pre compressed-tensors
From Source
git clone https://github.com/vllm-project/compressed-tensors
cd compressed-tensors
pip install -e .
Getting started
Saving a Compressed Model with PTQ
We can use compressed-tensors to run basic post training quantization (PTQ) and save the quantized model compressed on disk
model_name = "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cuda:0", torch_dtype="auto")
config = QuantizationConfig.parse_file("./examples/bit_packing/int4_config.json")
config.quantization_status = QuantizationStatus.CALIBRATION
apply_quantization_config(model, config)
dataset = load_dataset("ptb_text_only")["train"]
tokenizer = AutoTokenizer.from_pretrained(model_name)
def tokenize_function(examples):
return tokenizer(examples["sentence"], padding=False, truncation=True, max_length=1024)
tokenized_dataset = dataset.map(tokenize_function, batched=True)
data_loader = DataLoader(tokenized_dataset, batch_size=1, collate_fn=DefaultDataCollator())
with torch.no_grad():
for idx, sample in tqdm(enumerate(data_loader), desc="Running calibration"):
sample = {key: value.to(device) for key,value in sample.items()}
_ = model(**sample)
if idx >= 512:
break
model.apply(freeze_module_quantization)
model.apply(compress_quantized_weights)
output_dir = "./ex_llama1.1b_w4a16_packed_quantize"
compressor = ModelCompressor.from_pretrained_model(model)
compressor.compress_model(model)
model.save_pretrained(output_dir)
1 maintainer
Release files for compressed-tensors 0.14.1a20260323
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| compressed_tensors-0.14.1a20260323.tar.gz | 223.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| compressed_tensors-0.14.1a20260323-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 414.7 kB
Release files / compressed_tensors-0.14.1a20260323.tar.gz
| Download URL | compressed_tensors-0.14.1a20260323.tar.gz |
|---|---|
| Size | 223.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
be35b1fafe9f4311c90c57de936582aab9bd4a1fa467172fd2ecccae76912ea7
|
|
BLAKE2b-256 checksum How to use checksums |
a265b243132278ea92b79d02646f92bc2f1911a51b76142867f3d6b442e7db5a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Release files / compressed_tensors-0.14.1a20260323-py3-none-any.whl
| Download URL | compressed_tensors-0.14.1a20260323-py3-none-any.whl |
|---|---|
| Size | 190.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
276e41da3f001b2ce4dddebdeabb99fdef702c614a9e1f842c51c5df81a60bae
|
|
BLAKE2b-256 checksum How to use checksums |
349ff796c30c1ff5d106650f88bfdc4522c5912cbe81cbb5345f039ca976a4c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
