Skip to main content

Model Compression & Acceleration Module for sageLLM

Project description

sagellm-compression

Protocol Compliance (Mandatory)

CI PyPI version Python 3.10+ codecov

Model compression and acceleration tools for LLM inference.

Features

  • Quantization (INT8/INT4)
  • Sparsity (structured and unstructured pruning)
  • Speculative decoding
  • Kernel fusion
  • Chain-of-Thought acceleration

Installation

pip install isagellm-compression

Quick Start

from sagellm_compression import QuantizationConfig, apply_quantization

config = QuantizationConfig(method="int8", per_channel=True)
quantized_model = apply_quantization(model, config)

Development

git clone git@github.com:intellistream/sagellm-compression.git
cd sagellm-compression
./quickstart.sh

pip install -e ".[dev]"
pytest tests/ -v

Documentation

License

Private - IntelliStream Research Project

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

isagellm_compression-0.1.0.2-cp311-none-any.whl (3.6 kB view details)

Uploaded CPython 3.11

File details

Details for the file isagellm_compression-0.1.0.2-cp311-none-any.whl.

File metadata

File hashes

Hashes for isagellm_compression-0.1.0.2-cp311-none-any.whl
Algorithm Hash digest
SHA256 2373ab594cac32e81cd04c63c92008538bf6b7c5e31e6570a99b8dea1e05684f
MD5 2037f5ca959c6137b0c3b8cf81d2a198
BLAKE2b-256 b00639f630e246800055c06eb6d8e391aa958b9a1878e92b9349653db4dafb04

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page