Registry / ai-ml / openvino-genai

openvino-genai

library2026.2.1.0pypypi✓ verified 83d ago

OpenVINO GenAI provides optimized pipelines and execution methods for generative AI models (LLMs, image generation, etc.) leveraging Intel OpenVINO. Current version 2026.1.0.0, with quarterly releases. It enables efficient inference on Intel hardware.

ai-ml llm-agents

pip install openvino-genai

package ↗homepage ↗

INSTALL

IMPORT

SIG · OPENVINO-GENAI

openvino-genai

ai-mlpythonv2026.2.1.0

Install

6.4s avg

Import

652ms

Disk

282MB

Pass rate

5/ 10

Env Coverage5 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v2026.2.1.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 6.4s · import 0.652s · 280MB

282MB installed

● package 282MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

LLMPipeline

✓ from openvino_genai import LLMPipeline

✗ from openvino_genai.pipeline import LLMPipeline

LLMPipeline is directly under openvino_genai, not a submodule

VLMPipeline

✓ from openvino_genai import VLMPipeline

✗ from openvino_genai import VLM

Correct class name is VLMPipeline, not VLM

ImageGenerationPipeline

✓ from openvino_genai import ImageGenerationPipeline

✗ from openvino_genai import StableDiffusionPipeline

Use ImageGenerationPipeline for any image generation model

Basic LLM inference using OpenVINO GenAI. Ensure model is converted to OpenVINO IR format.

import openvino_genai from openvino_genai import LLMPipeline # Create pipeline with a model directory (assuming model files are present) pipeline = LLMPipeline("./tiny-llama") # Generate a response result = pipeline.generate("What is the capital of France?", max_new_tokens=100) print(result)

Debug

Known issues

breakingIn 2025.1.0, the `generate` method signature changed: `max_new_tokens` is now required (no longer defaults to 256). Code using older versions may fail with TypeError.

fix

Always pass `max_new_tokens` explicitly, e.g., `pipeline.generate(prompt, max_new_tokens=100)`.

affects: >=2025.1.0

breakingIn 2026.0.0, the `import openvino_genai.pipeline` was removed. You must import directly from openvino_genai.

fix

Use `from openvino_genai import LLMPipeline` instead of `from openvino_genai.pipeline import LLMPipeline`.

affects: >=2026.0.0

gotchaModel must be in OpenVINO IR format (`.xml` + `.bin`). Loading a Hugging Face model directly without conversion throws `RuntimeError: Model not in OpenVINO format`.

fix

Use `optimum-cli export openvino --model <hf-id> <output-dir>` to convert first.

affects: all

deprecated`openvino_genai.StableDiffusionPipeline` is deprecated in favor of `ImageGenerationPipeline` as of 2025.1.0.

fix

Replace `StableDiffusionPipeline` with `ImageGenerationPipeline`.

affects: >=2025.1.0

gotchaWhen using GPU (OpenVINO with GPU plugin), ensure that OpenCL runtime is installed and compatible with your Intel GPU.

fix

Install `openvino-2025.0.0` or later with GPU plugin; check `git clone` for GPU driver install scripts.

affects: all

Errors

Common errors & fixes

ImportError: cannot import name 'LLMPipeline' from 'openvino_genai'

Incorrect import path or missing installation (openvino-genai not installed).

fix

Run `pip install openvino-genai` and use correct import: `from openvino_genai import LLMPipeline`.

RuntimeError: Model not in OpenVINO format

Trying to load a Hugging Face model directly without converting to OpenVINO IR.

fix

Convert using `optimum-cli export openvino --model <model-id> <output-dir>` before loading.

TypeError: generate() missing required positional argument: 'max_new_tokens'

Using API version >=2025.1.0 where max_new_tokens became required.

fix

Pass `max_new_tokens` argument to generate method.

Upgrade

Version history

2026.2.1.0latest on PyPI · released Jun 17, 2026

Audit

Dependencies

openvinorequiredCore OpenVINO runtime required

transformersoptionalUsed for Hugging Face model compatibility

torchoptionalRequired for PyTorch model export/optimization

Agent activity

14 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/openvino-genai/ ↗

homepagehttps://docs.openvino.ai/2024/genai.html ↗