# microsoft/Llama-2-Onnx

Repository: https://github.com/microsoft/Llama-2-Onnx
Canonical: https://ross.abutalabs.com/products/llama-2-onnx
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-01-04T00:46:46+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 81
- inputs: {"age_days": 1143, "days_push": 973, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1026, forks 94 (observed 2026-08-28T04:03:16.740356+00:00)

## What it is
Microsoft's optimized ONNX export of Meta's Llama 2 models (7B and 13B, pretrained and fine-tuned, float16/float32), distributed via Git submodules with example code for running inference. It enables running Llama 2 with ONNX Runtime instead of the original PyTorch weights.

## Use cases
- run llama 2 with onnx runtime
- convert llama 2 to onnx format
- text generation with llama 2 on cpu or gpu
- deploy llama 2 without pytorch
- try llama 2 inference examples
- benchmark llama 2 onnx performance

## When to choose
- you want to run Llama 2 using ONNX Runtime for optimized inference
- you need pretrained or fine-tuned 7B/13B Llama 2 weights in ONNX format
- you want a minimal example of LLM text completion with ONNX

## When to avoid
- you need other LLMs than Llama 2
- you want to fine-tune or train models rather than run inference
- you cannot accept the gated access and Llama Community License restrictions
- you need the latest models like Llama 3

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning, deep-learning
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cross-platform
- tags: onnx, llama-2, model-optimization, inference, microsoft

## Member repositories
- microsoft/Llama-2-Onnx (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.740356+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 2026-08-30T07:07:58.976041+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Llama-2-Onnx (fetched 2026-08-28T04:03:16.740356+00:00, sha 8a33d314d8aa)
- Data as of 2026-08-30T08:39:29.467469+00:00.