Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

SmoothQuant enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLMs, including OPT-175B, BLOOM-176B, GLM-130B, and MT-NLG 530B.

Metadata

Release files for smoothquant 0.0.1.dev0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for smoothquant 0.0.1.dev0
File Interpreter ABI Platform
smoothquant-0.0.1.dev0-py3-none-any.whl Python 3 none any Details

Release files / smoothquant-0.0.1.dev0-py3-none-any.whl

Download URL smoothquant-0.0.1.dev0-py3-none-any.whl
Size 1.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
2281ba9f4f6c3463f2258b8de1b8fa8a1e73e008d764f73f24d415cc688cf865
BLAKE2b-256 checksum
How to use checksums
baff1e9097dc819baf2ba154ce23f62e20f0cff2932af05a6e2f52eef4e423b2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.16

Release history Release notifications | RSS feed

This release

0.0.1.dev0 This release

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page