Aviator is d-Matrix’s software stack for compiling, deploying, and managing AI inference on Corsair hardware.
Aviator is the software stack used to deploy models on d-Matrix Corsair inference hardware. It integrates with PyTorch and Triton DSL and draws on MLIR, OpenBMC, and other open-source technologies. Its components prepare models, compress numerical representations, compile workloads, and execute distributed inference across d-Matrix devices.
The stack includes model templates, a compression toolkit, compiler, inference engine, host runtime, chip runtime, and deployment tools. These components coordinate host interactions and device execution while helping operators analyze workload performance. Aviator serves developers and infrastructure teams building inference systems around Corsair cards, servers, and rack configurations.
| Attribute | Aviator | ONNX Runtime | ROCm | TensorRT | |
|---|---|---|---|---|---|
| Provider |  |  |  |  | |
| Founded | 2019 | 1975 | 1969 | 1993 | |
| Sells To | Enterprise | Enterprises, Small Business | Consumers, Enterprise | Consumers, Enterprise | |
| Pricing Model | — | SaaS, Transactional | Software, Transactional | Licensing, Product Sales, Subscription | |
| Ownership | Private | Public | Public | Public |
Provider
Founded 2019
Sells To Enterprise
Pricing Model —
Ownership Private
Provider
Founded 1975
Sells To Enterprises, Small Business
Pricing Model SaaS, Transactional
Ownership Public
Provider
Founded 1969
Sells To Consumers, Enterprise
Pricing Model Software, Transactional
Ownership Public
Provider
Founded 1993
Sells To Consumers, Enterprise
Pricing Model Licensing, Product Sales, Subscription
Ownership Public
Meta's on-device machine-learning runtime for mobile and edge devices.
Intel oneAPI is a unified open multiarchitecture software stack for AI and accelerated computing across Intel CPUs, GPUs, and accelerators.
Software suite for developing and deploying physical AI applications on SiMa.ai hardware.
An open-source LLM inference engine with hand-tuned kernels and speculative decoding for consumer hardware.
Amazon Bedrock is AWS's managed service for building applications with foundation models.
Gemini Enterprise Agent Platform supports building, deploying, and governing enterprise AI agents and machine learning models.
Open-source platform for collaborating on machine learning models, datasets, and applications.
AI platform that understands business, data, and goals
Meta's on-device machine-learning runtime for mobile and edge devices.
Hermes is PrismML's agentic inference stack for running on-device models.
Intel oneAPI is a unified open multiarchitecture software stack for AI and accelerated computing across Intel CPUs, GPUs, and accelerators.
Parallel computing platform and programming model for GPU-accelerated applications across HPC, AI, and graphics workloads.
Software suite for developing and deploying physical AI applications on SiMa.ai hardware.
An open-source LLM inference engine with hand-tuned kernels and speculative decoding for consumer hardware.
Amazon Bedrock is AWS's managed service for building applications with foundation models.
Gemini Enterprise Agent Platform supports building, deploying, and governing enterprise AI agents and machine learning models.
Open-source platform for collaborating on machine learning models, datasets, and applications.
