Model compilers & graph optimizers
Model compilers & graph optimizers covers compilers that convert and optimise a model to run fast on specific hardware, such as TensorRT, TVM, OpenVINO and XLA.
In brief
Model compilers & graph optimizers, in brief.
What it isModel compilers & graph optimizers covers compilers that convert and optimise a model to run fast on specific hardware, such as TensorRT, TVM, OpenVINO and XLA.
Where it sitsOne of 13 categories in the Inference and serving layer. Inference and serving is everything that turns a trained model into a running service: hosted inference providers, gateways that route between them, serving engines, and the tools that make models smaller and faster.
What we track24 products, including AMD MIGraphX, Apache TVM, Arm Vela compiler (Ethos-U), AWS Neuron SDK (neuronx-cc) and Core ML Tools.
The products
24 products in Model compilers & graph optimizers.
Each name opens a search for that product in our index.
ProductMakerIts own site
From our census of 2026-11-08. A product listed here is one that belongs in this category; the search answer says whether we have checked it.
Questions
Model compilers & graph optimizers, answered.
What is Model compilers & graph optimizers in AI infrastructure?Model compilers & graph optimizers covers compilers that convert and optimise a model to run fast on specific hardware, such as TensorRT, TVM, OpenVINO and XLA.
Which layer of AI infrastructure is Model compilers & graph optimizers in?Model compilers & graph optimizers is in the Inference and serving layer. Inference and serving is everything that turns a trained model into a running service: hosted inference providers, gateways that route between them, serving engines, and the tools that make models smaller and faster.
Which products are in Model compilers & graph optimizers?We track 24 products in Model compilers & graph optimizers, including AMD MIGraphX, Apache TVM, Arm Vela compiler (Ethos-U), AWS Neuron SDK (neuronx-cc), Core ML Tools, Edge Impulse EON Compiler, Hailo Dataflow Compiler and Hidet. The full list is on this page.
Inference and serving
The other categories in Inference and serving.
AI gateways & model routersBatch inferenceGenerative media inference platformsGenerative media workflow toolsInference benchmarking & load testingInference kernels & attention librariesInference providersKV-cache & prompt-caching infrastructureLoRA serving & adapter hubsOn-device / edge runtimesQuantization / optimizationServing engines & model servers