# intel/intel-extension-for-pytorch

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

Repository: https://github.com/intel/intel-extension-for-pytorch
Canonical: https://ross.abutalabs.com/products/intel-extension-for-pytorch
Language: Python
License: Apache-2.0
License Family: permissive
Topics: pytorch, neural-network, machine-learning, deep-learning, intel, quantization
Archived: true
Last push: 2026-03-30T08:35:24+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 30, longevity 100
- inputs: {"age_days": 2331, "days_push": 156, "days_rel": 386, "gap_med": 44.5, "n_releases_24m": 9}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2012, forks 324 (observed 2026-08-28T04:06:05.137371+00:00)

## What it is
A Python package extending official PyTorch with Intel-specific optimizations for CPUs and GPUs, including quantization and LLM inference acceleration. The project is now archived and retired, with most features upstreamed into PyTorch itself.

## Use cases
- speed up pytorch inference on intel cpus
- quantize pytorch models for intel hardware
- run llm inference faster on intel gpus
- optimize deep learning training on intel xeon
- get better pytorch performance on intel platforms

## When to choose
- you are stuck on an older PyTorch version that lacks Intel optimizations
- you maintain a legacy project that already depends on this package

## When to avoid
- starting any new project - use PyTorch directly instead
- you need ongoing support, bug fixes, or security patches
- you need official binary wheels or new releases
- you want actively maintained Intel hardware optimizations

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, llm-inference, gpu-computing
- domain: machine-learning, deep-learning, large-language-models, gpu-computing
- platform: python
- tags: pytorch, intel, quantization, archived, performance-optimization, linux, gpu

## Member repositories
- intel/intel-extension-for-pytorch (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:05.137371+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 2026-08-30T03:01:02.178669+00:00, confidence not recorded.
  - readme: https://github.com/intel/intel-extension-for-pytorch (fetched 2026-08-28T04:06:05.137371+00:00, sha 491997d3a371)
  - registry_pypi: https://pypi.org/pypi/intel-extension-for-pytorch/json (fetched 2026-08-29T10:40:56.109913+00:00, sha 67d8b5b4af87)
- Data as of 2026-08-30T08:39:29.467469+00:00.