Loading...
Please wait a moment
Founded by passionate advocates of learning and innovation, Learni set out to make professional training accessible to everyone, everywhere in the world. Our team works in the largest cities such as Paris, Lyon, Marseille, and internationally, to support talents and organizations in their skills development.
10 spots per session maximum — 10 already taken
Which format do you prefer?
30 free minutes with a training advisor — no commitment.
Loading available slots...
Professional Training training in Memphis in October 2026 with Learni. Certified, expert trainers, eligible for employer funding. Free quote.
Discover why customer journey mapping training is essential for marketing teams in March 2026. Learn step-by-step guides, tools, trends, and strategies to boost customer experience and revenue.
Discover how design thinking training programs in March 2026 will equip innovation teams with cutting-edge skills for problem-solving, collaboration, and breakthrough creativity in a rapidly evolving business landscape.
Discover essential strategies, trends, and training programs for organizations to excel in data governance by March 2026. Stay compliant and leverage data effectively.
Don't let this gap widen
Failing to master ONNX Runtime exposes ML inference pipelines to severe inefficiencies, where unoptimized models suffer from 3-5x higher latency and resource consumption.
Industry data reveals that 68% of production ML incidents trace back to suboptimal inference engines, averaging $750,000 in annual cloud costs and downtime losses per team.
Without this expertise, companies face stalled deployments, eroded market share, and career-stifling project failures—every month of delay amplifies these multimillion-dollar risks.
The Training in ONNX Runtime training is delivered in-person or remotely (blended-learning, e-learning, virtual classroom, remote in-person). At Learni, a Qualiopi-certified training organization, each program is designed to maximize skills acquisition, regardless of the training mode chosen.
The trainer alternates between demonstrative, interrogative, and active methods (through practical exercises and/or real-world scenarios). This pedagogical approach ensures concrete and directly applicable learning in the workplace.
To ensure the quality of the Training in ONNX Runtime training, Learni provides the following teaching resources:
For in-house training at a location external to Learni, the client ensures and commits to having all necessary teaching materials (IT equipment, internet connection...) for the proper conduct of the training action in accordance with the prerequisites indicated in the communicated training program.
The assessment of skills acquired during the Training in ONNX Runtime training is carried out through:
Learni is committed to the accessibility of its professional training programs. All our training programs are accessible to people with disabilities. Our teams are available to adapt teaching methods to your specific needs. Do not hesitate to contact us for any accommodation request.
Learni training programs are available for inter-company and intra-company settings, both in-person and remote. Registration is possible up to 48 business hours before the start of training. Our programs are eligible for OPCO, Pôle emploi, and FNE-Formation funding. Contact us to discuss your training project and funding possibilities.
Discover ONNX Runtime. Standardize your ML models. Master the ONNX format. Learn advanced basics. Install ONNX Runtime in Python. Configure for intermediate projects. Explore main APIs. Test first runs. Optimize workflow from day 1. ONNX Runtime training accelerates your deployments. Use PyTorch-TensorFlow to ONNX conversion tools. Validate converted models. Handle common errors. Boost ML productivity. Practice on real datasets. Create ONNX Runtime sessions. Load ONNX models simply. Run fast inferences. Measure initial latencies. Prepare for future optimizations. This session lays solid foundations. Practical workshops included. Expert teaching support. Advance to professional performance.
Run advanced ONNX models. Use dynamic sessions. Manage input and output tensors. Apply CPU providers. Optimize with graph optimizations. Reduce model sizes. Accelerate inferences by 20%. Intermediate ONNX Runtime training covers this in depth. Integrate NumPy for data preparation. Efficient batch processing. Manage multi-threading. Test on various hardware. Debug slow inferences. Profile performance accurately. Use ONNX Runtime tools. Convert complex models. Seamless PyTorch to ONNX. Smooth TensorFlow SavedModels. Daily hands-on exercises. Create inference pipelines. Validate accuracy post-conversion. Manage model versions. Boost deployment speed. Interactive sessions. Expert guidance on your progress. Master professional execution.
Switch to GPU with CUDA. Activate TensorRT provider. Set up CUDA Execution Provider. Boost inferences by 10x. ONNX Runtime training optimizes hardware. DirectML for Windows GPU. ROCm for AMD. Compare provider performance. Select optimal ones for projects. Graph fusion techniques. Deep dive into operator optimizations. Reduce memory usage. Minimal latencies. Real benchmarks on datasets. Integrate Intel OpenVINO. Seamless cross-platform. Advanced C++ bindings. Expert Python wrappers. Hands-on GPU exercises. Deploy to edge devices. ONNX mobile inference. Android and iOS support. Profile multi-GPU. Scale ML applications. Achieve immediate performance gains. Intensive practical workshops. Progress rapidly.
Integrate ONNX Runtime into Python apps. Flask and FastAPI servers. Production-ready inference. Master C++ API. Build native projects. Ultimate performance. Intermediate ONNX Runtime training excels here. JavaScript WebAssembly. Node.js servers. Cross-language power. Dockerize deployments. Kubernetes scaling. ONNX CI/CD pipelines. Monitor inferences live. Robust error handling. Security best practices. Data preprocessing pipelines. Post-processing outputs. Model serving patterns. ML microservices. Real hands-on projects. Develop inference APIs. Test high loads. Optimize throughput. Avoid vendor lock-in. ONNX universal standard. Boost your ML engineer career. Intensive coding sessions. Continuous expert feedback.
Deploy ONNX Runtime to production. Cloud AWS, Azure, GCP. Serverless inferences. Edge computing and IoT. ONNX Runtime training ends strong. Model quantization to INT8. Advanced pruning techniques. Knowledge distillation in ONNX. Ensemble model fusion. Create custom ops. Extend ONNX Runtime. Expert troubleshooting. Ultimate performance tuning. Integrated monitoring tools. A/B testing models. Live model updates. Zero-downtime deploys. Real industry case studies. Computer vision, NLP, audio ML. Scale to millions of inferences. Optimize cloud costs. Measure rapid ROI. Certificate upon completion. Build portfolio projects. ML alumni network. Accelerate your career.
Target audience
Intermediate ML developers optimizing model inference
Prerequisites
Proficiency in Python. Basics in PyTorch or TensorFlow. Knowledge of ONNX recommended
Loading...
Please wait a moment





























