Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/optimum
Library/optimumForked

huggingface/optimum

optimum

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

View on GitHub↗Upstream huggingface/optimum↗

Builder

HuggingFace

HuggingFace

huggingface • ai-lab

Stars

3,402

Using upstream star count

Forks

648

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Jul 20, 2021

Project creation date

README Summary

<!--- Copyright 2025 The HuggingFace Team. All rights reserved.

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Computer Vision ModelsDeep Learning Framework IntegrationDiffusion ModelsGPU ComputingHardware AccelerationInference OptimizationModel OptimizationONNX Model ConversionPerformance ProfilingQuantization TechniquesSentence EmbeddingsTraining AccelerationTransformer Architecture

Tags

Computer Vision ModelsDeep Learning Framework IntegrationDiffusion ModelsGPU ComputingHardware AccelerationInference OptimizationModel OptimizationONNX Model ConversionPerformance ProfilingQuantization TechniquesSentence EmbeddingsTraining AccelerationTransformer ArchitectureDeep LearningDockerForkedHuggingFaceInferenceLarge Language ModelsLoRA / PEFTMobileNode.jsONNXPyTorchPythonQuantizationTensorRTTransformers

Taxonomy

AI Trends

Model EfficiencyEdge AIProduction AI SystemsHardware-aware AIDemocratized AI Deployment

category

Foundation ModelsModel TrainingInference & ServingMLOps & InfrastructureDev Tools & Automation

Deployment Context

Cloud APISelf-hostedEdge/MobileOn-premise

Modalities

TextImageMultimodal

Skill Areas

Model OptimizationHardware AccelerationTransformer ArchitectureDiffusion ModelsComputer Vision ModelsSentence EmbeddingsInference OptimizationTraining AccelerationPerformance ProfilingQuantization TechniquesONNX Model ConversionGPU ComputingDeep Learning Framework Integration

tag

Deep LearningDockerForkedHuggingFaceInferenceLarge Language ModelsLoRA / PEFTMobileModel OptimizationNode.jsONNXPyTorchPythonQuantizationTensorRTTransformers

Use Cases

Production Model ServingReal-time Inference OptimizationCost-effective Model DeploymentEdge Device Model OptimizationLarge-scale Training AccelerationMulti-hardware Model DeploymentPerformance BenchmarkingModel Conversion and Export

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

3

Transformers v5 (#2408)

Ella Charlaix • Mar 13, 2026

ec676fd

Remove optimum-amd from documentation (#2413)

Ella Charlaix • Mar 13, 2026

92c00b5

docs: add empirical energy efficiency data to quantization concept guide (#2410)

hongping-zh • Mar 11, 2026

481262f

Quality

production
Quality
high
Maturity
production

Categories

Foundation ModelsPrimaryInference & ServingModel TrainingMLOps & InfrastructureDev Tools & AutomationEdge & Mobile AIOther AI / ML

PM Skills

Cost & EfficiencyScale & Reliability

Languages

Python100.0%

Timeline

Project created
Jul 20, 2021
Forked
Mar 22, 2026
Your last push
2 months ago
Upstream last push
16 days ago
Tracked since
Mar 13, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…