RepoMicrosoftMicrosoftpublished May 22, 2025seen 5d

microsoft/olive-recipes

Python

Open original ↗

Captured source

source ↗
published May 22, 2025seen 5dcaptured 10hhttp 200method plain

microsoft/olive-recipes

Language: Python

License: MIT

Stars: 57

Forks: 52

Open issues: 73

Created: 2025-05-22T18:25:04Z

Pushed: 2026-06-11T03:19:35Z

Default branch: main

Fork: no

Archived: no

README:

This repository compliments Olive, the AI model optimization toolkit, and includes recipes demonstrating its extensive features and use cases. Users of Olive can use these recipes as a reference to either optimize publicly available AI models or to optimize their own proprietary models.

Supported models, architectures, devices and execution providers

Below are list of available recipes grouped by different criteria. Click the link to expand.

Models grouped by model architecture

| bert | clip | deepseek | gemma | hiera | llama | llama3 | mistral | mobilenet | phi3 | phi4 | qwen2 | resnet | sam | sd | vit | whisper | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | [google-bert-bert-base-multilingual-cased](google-bert-bert-base-multilingual-cased/QNN) | [OFA-Sys-chinese-clip-vit-base-patch16](OFA-Sys-chinese-clip-vit-base-patch16/aitk) | [deepseek-ai-DeepSeek-R1-Distill-Llama-8B](deepseek-ai-DeepSeek-R1-Distill-Llama-8B/aitk) | [google-gemma-3-1b-it](google-gemma-3-1b-it/OpenVINO) | [sam2.1-hiera-small](sam2.1-hiera-small/QNN) | [deepseek-ai-DeepSeek-R1-Distill-Llama-8B](deepseek-ai-DeepSeek-R1-Distill-Llama-8B/NvTensorRtRtx) | [meta-llama-Llama-3.1-8B-Instruct](meta-llama-Llama-3.1-8B-Instruct/aitk) | [mistralai-Mistral-7B-Instruct-v0.2](mistralai-Mistral-7B-Instruct-v0.2/NvTensorRtRtx) | [timm-mobilenetv3_small_100.lamb_in1k](timm-mobilenetv3_small_100.lamb_in1k/VitisAI) | [microsoft-Phi-3-mini-128k-instruct](microsoft-Phi-3-mini-128k-instruct/NvTensorRtRtx) | [microsoft-Phi-4-mini-instruct](microsoft-Phi-4-mini-instruct/NvTensorRtRtx) | [Qwen-Qwen2.5-0.5B-Instruct](Qwen-Qwen2.5-0.5B-Instruct/NvTensorRtRtx) | [microsoft-resnet-50](microsoft-resnet-50/aitk) | [sam-vit-base](sam-vit-base/aitk) | [sd-legacy-stable-diffusion-v1-5](sd-legacy-stable-diffusion-v1-5/aitk) | [google-vit-base-patch16-224](google-vit-base-patch16-224/OpenVINO) | [openai-whisper-large-v3-turbo](openai-whisper-large-v3-turbo/OpenVINO) | | [google-bert-bert-base-multilingual-cased](google-bert-bert-base-multilingual-cased/aitk) | [laion-CLIP-ViT-B-32-laion2B-s34B-b79K](laion-CLIP-ViT-B-32-laion2B-s34B-b79K/QNN) | [deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B](deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/QNN) | | | [meta-llama-Llama-3.1-8B-Instruct](meta-llama-Llama-3.1-8B-Instruct/NvTensorRtRtx) | [meta-llama-Llama-3.2-1B-Instruct](meta-llama-Llama-3.2-1B-Instruct/QNN) | [mistralai-Mistral-7B-Instruct-v0.2](mistralai-Mistral-7B-Instruct-v0.2/aitk) | | [microsoft-Phi-3-mini-128k-instruct](microsoft-Phi-3-mini-128k-instruct/QNN) | [microsoft-Phi-4-mini-instruct](microsoft-Phi-4-mini-instruct/aitk) | [Qwen-Qwen2.5-0.5B-Instruct](Qwen-Qwen2.5-0.5B-Instruct/aitk) | | [sam2.1-hiera-small](sam2.1-hiera-small/aitk) | [sd2-community-stable-diffusion-2-1](sd2-community-stable-diffusion-2-1/aitk) | [google-vit-base-patch16-224](google-vit-base-patch16-224/QNN) | [openai-whisper-large-v3-turbo](openai-whisper-large-v3-turbo/aitk) | | [intel-bert-base-uncased-mrpc](intel-bert-base-uncased-mrpc/QNN) | [laion-CLIP-ViT-B-32-laion2B-s34B-b79K](laion-CLIP-ViT-B-32-laion2B-s34B-b79K/aitk) | [deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B](deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk) | | | [meta-llama-Llama-3.2-1B-Instruct](meta-llama-Llama-3.2-1B-Instruct/NvTensorRtRtx) | [meta-llama-Llama-3.2-1B-Instruct](meta-llama-Llama-3.2-1B-Instruct/aitk) | [mistralai-Mistral-7B-Instruct-v0.3](mistralai-Mistral-7B-Instruct-v0.3/aitk) | | [microsoft-Phi-3-mini-128k-instruct](microsoft-Phi-3-mini-128k-instruct/aitk) | [microsoft-Phi-4-mini-instruct](microsoft-Phi-4-mini-instruct/olive) | [Qwen-Qwen2.5-0.5B](Qwen-Qwen2.5-0.5B/aitk) | | | | [google-vit-base-patch16-224](google-vit-base-patch16-224/aitk) | [openai-whisper-large-v3-turbo](openai-whisper-large-v3-turbo/olive) | | [intel-bert-base-uncased-mrpc](intel-bert-base-uncased-mrpc/aitk) | [openai-clip-vit-base-patch16](openai-clip-vit-base-patch16/QNN) | [deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B](deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/olive) | | | | [meta-llama-Llama-3.2-1B-Instruct](meta-llama-Llama-3.2-1B-Instruct/olive) | | | [microsoft-Phi-3-mini-4k-instruct](microsoft-Phi-3-mini-4k-instruct/NvTensorRtRtx) | [microsoft-Phi-4-mini-reasoning](microsoft-Phi-4-mini-reasoning/aitk) | [Qwen-Qwen2.5-1.5B-Instruct](Qwen-Qwen2.5-1.5B-Instruct/NvTensorRtRtx) | | | | [sam-vit-base](sam-vit-base/QNN) | | | | [openai-clip-vit-base-patch16](openai-clip-vit-base-patch16/aitk) | [deepseek-ai-DeepSeek-R1-Distill-Qwen-14B](deepseek-ai-DeepSeek-R1-Distill-Qwen-14B/aitk) | | | | [meta-llama-Meta-Llama-3-8B](meta-llama-Meta-Llama-3-8B/olive) | | | [microsoft-Phi-3-mini-4k-instruct](microsoft-Phi-3-mini-4k-instruct/QNN) | [microsoft-Phi-4-reasoning-plus](microsoft-Phi-4-reasoning-plus/aitk) | [Qwen-Qwen2.5-1.5B-Instruct](Qwen-Qwen2.5-1.5B-Instruct/QNN) | | | | | | | | [openai-clip-vit-base-patch32](openai-clip-vit-base-patch32/QNN) | [deepseek-ai-DeepSeek-R1-Distill-Qwen-7B](deepseek-ai-DeepSeek-R1-Distill-Qwen-7B/aitk) | | | | | | | [microsoft-Phi-3-mini-4k-instruct](microsoft-Phi-3-mini-4k-instruct/aitk) | [microsoft-Phi-4-reasoning](microsoft-Phi-4-reasoning/aitk) | [Qwen-Qwen2.5-1.5B-Instruct](Qwen-Qwen2.5-1.5B-Instruct/aitk) | | | | | | | | [openai-clip-vit-base-patch32](openai-clip-vit-base-patch32/aitk) | | | | | | | | [microsoft-Phi-3.5-mini-instruct](microsoft-Phi-3.5-mini-instruct/NvTensorRtRtx) | [microsoft-Phi-4](microsoft-Phi-4/OpenVINO) | [Qwen-Qwen2.5-1.5B-Instruct](Qwen-Qwen2.5-1.5B-Instruct/olive) | | | | | | | | [openai-clip-vit-large-patch14](openai-clip-vit-large-patch14/aitk) | | | | | | | | [microsoft-Phi-3.5-mini-instruct](microsoft-Phi-3.5-mini-instruct/QNN) | [microsoft-Phi-4](microsoft-Phi-4/aitk) | [Qwen-Qwen2.5-14B-Instruct](Qwen-Qwen2.5-14B-Instruct/NvTensorRtRtx) | | | | | | | | | | | | | | | | [microsoft-Phi-3.5-mini-instruct](microsoft-Phi-3.5-mini-instruct/aitk) | | [Qwen-Qwen2.5-14B-Instruct](Qwen-Qwen2.5-14B-Instruct/aitk) | | | | | | | | | | | | | | | | [microsoft-Phi-3.5-mini-instruct](microsoft-Phi-3.5-mini-instruct/olive) | | [Qwen-Qwen2.5-3B-Instruct](Qwen-Qwen2.5-3B-Instruct/aitk) | | | | | | | | | | | | | | | |…

Excerpt shown — open the source for the full document.

Notability

notability 3.0/10

Low stars, routine repo by Microsoft