Refiant

TensorMesh

This company develops software that manages and reuses computed inference data to reduce large language model processing costs for enterprise artificial intelligence developers.

Minima AI

This company develops model-optimisation and inference software that reduces memory usage and costs for enterprise developers running large language models.

OpenInfer.io

This company develops a unified inference software stack for developers and enterprises to run large language models across heterogeneous edge and cloud infrastructure.

PrismML

The company develops high-performance 1-bit and ternary large language models for developers and enterprises seeking efficient, on-device artificial intelligence across consumer and industrial hardware.

Pruna AI

This company provides a software platform to help businesses and developers compress, optimize and run machine learning models for more efficient inference.

Roofline

This company develops a compiler stack and deployment platform that enables software developers to run artificial intelligence models across various edge hardware chips.

OmniML

This company develops software that compresses and optimises machine learning models to enable faster artificial intelligence deployment on resource-constrained edge devices for enterprise hardware manufacturers.

Strong Compute

This company develops a platform to manage and reduce GPU cloud costs and token expenditure for machine learning teams.