# ELS-RD/transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

Repository: https://github.com/ELS-RD/transformer-deploy
Canonical: https://ross.abutalabs.com/products/transformer-deploy
Homepage: https://els-rd.github.io/transformer-deploy/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: inference, deep-learning, natural-language-processing, deployment, machine-learning, server
Last push: 2024-10-23T17:41:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1767, "days_push": 679, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1689, forks 153 (observed 2026-08-28T04:05:22.386177+00:00)

## What it is
A Python tool that optimizes Hugging Face transformer models for production inference using ONNX Runtime and NVIDIA TensorRT, deploying them on NVIDIA Triton inference servers. It claims 5-10X speedups over vanilla PyTorch with a single command line workflow.

## Use cases
- deploy hugging face transformer models to production
- speed up transformer inference on gpu
- convert pytorch models to onnx or tensorrt
- serve sentence embeddings with low latency
- quantize transformer models for cpu and gpu
- set up a triton inference server for nlp models

## When to avoid
- you only need occasional or offline inference without strict latency requirements
- you do not use NVIDIA GPUs or Triton-compatible infrastructure
- your model cannot be exported to ONNX
- you need a fully managed inference service rather than self-hosted deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning, deployment, cli
- domain: machine-learning, deep-learning
- platform: python
- tags: hugging-face, onnx, tensorrt, triton-inference-server, quantization, model-optimization, natural-language-processing, devops, linux, docker, gpu

## Member repositories
- ELS-RD/transformer-deploy (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:22.386177+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 2026-08-30T03:38:39.710720+00:00, confidence not recorded.
  - readme: https://github.com/ELS-RD/transformer-deploy (fetched 2026-08-28T04:05:22.386177+00:00, sha 4955ae446878)
  - homepage: https://els-rd.github.io/transformer-deploy/ (fetched 2026-08-29T11:13:30.487410+00:00, sha 2017b2857f0b)
- Data as of 2026-08-30T08:39:29.467469+00:00.