🎁Azure · AWS · Google — 1 free certification per learner, up to $400.Get the offer →
← Back

Training ONNX Runtime - Optimizing AI Inference in Production

Ref: IYC763
10 people max.
7000€ HT / per person
−15% from 2 people−30% from 3 people−50% from 5 people
Pay in 3 installments · +$170/day onsite · +$500 with certification exam
5 journées
distanciel

Share in 2 clicks

EquansAptarArcelorMittalUbisoftINSEECLa PlateformeCESIEFREIEPSIINGETISMy Digital SchoolYnovEquansAptarArcelorMittalUbisoftINSEECLa PlateformeCESIEFREIEPSIINGETISMy Digital SchoolYnov

Learning objectives

  • Master ONNX Runtime for ultra-high-performance AI inferences in enterprise settings
  • Optimize ONNX models using advanced quantization and pruning techniques
  • Develop scalable inference pipelines on CPU, GPU, and NPU
  • Implement ONNX Runtime in production with monitoring and security
  • Design hybrid ONNX integrations for certified applications
  • Deploy ONNX Runtime solutions compatible with cloud and edge
  • Acquire professional skills in advanced ONNX troubleshooting

The Learni story

Founded by passionate learning and innovation experts, Learni's mission is to make professional training accessible to everyone, anywhere in the world. Our team operates in major hubs — London, New York, Boston — and internationally, to support talents and organizations in upskilling.

Don't let this gap widen

Why this program matters

  • Without this upskilling, your team accumulates a technological gap that translates directly into productivity loss.

  • Organizations that don't train their talents on key topics see their competitiveness drop.

  • Every quarter without training is a gap widening with competitors who invest.

  • The cost of inaction quickly exceeds that of well-targeted training.

Fouzi Benzidane
Fouzi Benzidane

Learni Trainer · Expert

73%productivity gap
×3cost of inaction

Program

Module 1ONNX Runtime Advances 2026: Expert Configuration and Basic Optimizations (CLI Tools, C++/Python APIs)

Dive into the new features of ONNX Runtime 2026, install and configure the advanced environment with support for emerging NPUs, explore expert APIs in Python and C++ for custom builds, perform initial benchmarks on converted TensorFlow/PyTorch models, produce a baseline performance report and automation script, apply optimization flags to reduce latency from the first practical exercise on a real enterprise case.

Module 2ONNX Runtime Performance: Quantization and Graph Optimizations (ORTModule, Transformer APIs)

Optimize your ONNX models using dynamic and static quantization with ONNX Runtime tools, transform complex graphs using ORTModule for PyTorch, test advanced operator fusions on GPU CUDA and DirectML, measure gains up to 4x in speed on large datasets, develop an automated post-training quantization pipeline, analyze precision/speed trade-offs through hands-on exercises, and generate production-ready deliverables.

Module 3ONNX Runtime Hardware: GPU/NPU/Edge Acceleration (TensorRT, OpenVINO, DirectML Backends)

Integrate ONNX Runtime with expert hardware backends like TensorRT for NVIDIA, OpenVINO for Intel, and DirectML for Windows, configure multi-EP sessions for CPU/GPU/NPU hybridization, deploy on edge devices with memory constraints, perform cross-platform benchmarks on industrial IoT cases, optimize for low-latency real-time inference, produce a scalable prototype with integrated monitoring, and validate performance through simulated load-balanced tests.

Module 4ONNX Runtime Deployment: Scaling and Security in Production (Kubernetes, Docker, Prometheus Monitoring)

Deploy ONNX Runtime in a Kubernetes cluster with secure Docker containers, implement auto-scaling based on inference metrics, integrate Prometheus/Grafana monitoring for latency and throughput, manage model security via encryption and access controls, test fault-tolerance in high-availability scenarios, develop a CI/CD pipeline for over-the-air model updates, and finalize a ready-to-use production architecture blueprint for your enterprise.

Module 5Advanced ONNX Runtime Cases: Troubleshooting and Custom Extensions (Profiling, Plugins, Interoperability)

Master expert troubleshooting with ONNX Runtime trace profiling and advanced debuggers, develop custom Execution Providers for proprietary hardware, explore interoperability with frameworks like Hugging Face and MLflow, resolve common pitfalls in multi-threading and memory leaks, apply to a complete ongoing project, produce certifying documentation and a maintenance plan, consolidate skills through code review and final MCQ for professional certification.

Evaluation method

  • Expert MCQ to validate acquired knowledge at the end of the training
  • Continuous evaluation through practical exercises and benchmarks
  • Presentation of the ongoing ONNX Runtime project to the trainer

Learning method

  • Courses led by an active ONNX Runtime expert trainer
  • Practical exercises based on real enterprise AI cases
  • Progressive ongoing project throughout the training
  • Complete course materials provided to each participant

Methods, materials and delivery

The Training ONNX Runtime - Optimizing AI Inference in Production program is delivered onsite or remote (blended-learning, e-learning, virtual classroom, remote presence). At Learni, an industry-certified training organization, every program is built to maximize skills acquisition regardless of the chosen format.

The trainer alternates between demonstrative, interrogative and active methods (through hands-on labs and/or scenarios). This pedagogical approach guarantees concrete learning that's immediately applicable at work.

Equipment required

For the smooth delivery of the Training ONNX Runtime - Optimizing AI Inference in Production program, the following equipment is required:

  • Mac or PC computers, high-speed fiber internet, whiteboard or flipchart, projector or interactive touch screen (for remote sessions)
  • Training environments installed on workstations or accessible online
  • Course materials, hands-on exercises and complementary resources
  • Post-training access to materials and educational resources

For intra-company training on a site outside Learni, the client commits to providing all required teaching materials (computers, internet, etc.) for the smooth delivery of the program in line with the prerequisites in the communicated program.

* contact us for remote delivery feasibility** ratio varies depending on the program

Skills assessment methods

Assessment of skills acquired during the Training ONNX Runtime - Optimizing AI Inference in Production program is performed through:

  • During training: case studies, hands-on labs and professional scenarios
  • End of training: self-assessment questionnaire and skills evaluation by the trainer
  • After training: completion certificate detailing acquired skills

Program accessibility

Learni is committed to making its programs accessible. All our programs are accessible to people with disabilities. Our teams are available to adapt the pedagogical methods to your specific needs. Please contact us for any adjustment request.

Enrollment terms and lead times

Learni programs are available inter-company and intra-company, onsite or remote. Enrollments are possible up to 48 business hours before the program starts. Our programs are eligible for corporate funding paths. Contact us to discuss your training project and funding options.

Verified reviews

What our learners

4.9 · +100 verified reviews
★★★★★

« cool, j'ai appris des trucs »

TomFormation AWS — Cloud Practitioner
★★★★★

« j'etais perdu au debut mais Ramy Saharaoui m'a pas laché, il a pris le temps. merci vraiment »

Eva CarpentierFormation LLM en Entreprise — Claude, ChatGPT, Mistral
★★★★★

« la formation dev etait intense mais grave bien. merci Anthony Khelil »

NolanDWWM - Développeur Web et Web Mobile
★★★★★

« 😊👍 »

AmbreDWWM - Développement Web & Mobile React
★★★★★

« bien 👍 »

Léo BlanchardFormation AWS — DevOps Engineer Professional
★★★★★

« Allan Busi t'es au top, continue comme ça. formation géniale »

MargotFormation Claude & ChatGPT — Comparatif et Cas d'Usage
★★★★★

« cool, j'ai appris des trucs »

TomFormation AWS — Cloud Practitioner
★★★★★

« j'etais perdu au debut mais Ramy Saharaoui m'a pas laché, il a pris le temps. merci vraiment »

Eva CarpentierFormation LLM en Entreprise — Claude, ChatGPT, Mistral
★★★★★

« la formation dev etait intense mais grave bien. merci Anthony Khelil »

NolanDWWM - Développeur Web et Web Mobile
★★★★★

« 😊👍 »

AmbreDWWM - Développement Web & Mobile React
★★★★★

« bien 👍 »

Léo BlanchardFormation AWS — DevOps Engineer Professional
★★★★★

« Allan Busi t'es au top, continue comme ça. formation géniale »

MargotFormation Claude & ChatGPT — Comparatif et Cas d'Usage
★★★★★

« cool, j'ai appris des trucs »

TomFormation AWS — Cloud Practitioner
★★★★★

« j'etais perdu au debut mais Ramy Saharaoui m'a pas laché, il a pris le temps. merci vraiment »

Eva CarpentierFormation LLM en Entreprise — Claude, ChatGPT, Mistral
★★★★★

« la formation dev etait intense mais grave bien. merci Anthony Khelil »

NolanDWWM - Développeur Web et Web Mobile
★★★★★

« 😊👍 »

AmbreDWWM - Développement Web & Mobile React
★★★★★

« bien 👍 »

Léo BlanchardFormation AWS — DevOps Engineer Professional
★★★★★

« Allan Busi t'es au top, continue comme ça. formation géniale »

MargotFormation Claude & ChatGPT — Comparatif et Cas d'Usage
Read all reviews
Our method

Training quality, guaranteed at every step

Before, during, after: we frame the brief, introduce the trainer, tailor the content and measure impact. You stay in control from kickoff to wrap-up.

Step 1

Rigorous trainer selection

Each trainer is validated on three criteria: hands-on field expertise, proven pedagogy and alignment with your industry.

  • Triple validation: technical, pedagogical, sectoral.
  • Minimum rating 4.8/5 over the last 12 sessions.
Step 2

You meet the trainer beforehand

30-minute video call between you and the selected trainer to validate the fit, adjust content and clear any final doubts.

  • Live briefing on goals and team context.
  • Veto right — we swap the trainer for free if needed.
Step 3

Content tailored to your context

No recycled slides. The syllabus is reworked from your real cases: tools, constraints, vocabulary, ongoing projects.

  • Hands-on cases drawn from your stack and projects.
  • Program co-written then validated by your team.
Step 4

Continuous quality follow-up

Live evaluations, 30/90/180-day check-ins and a consolidation plan. If the impact misses the mark, we rework it.

  • NPS, knowledge quizzes and skills self-assessment.
  • Satisfaction guarantee: fully satisfied or free rework.

A simple promise: you don't pay to discover the trainer on day one. Everything is validated upfront, by you.

Your professional training, anywhere

Let's build
your next
program.

30 minutes with a learning advisor. No commitment. No sales pitch dressed up as a demo.

Reply within 24 h · Industry-certified · Corporate funding
WhatsApp