YC W25
Exla
An SDK to run transformer models anywhere
About
Exla aggressively quantizes AI models to minimize memory usage and maximize inference speed. Whether you're deploying LLMs, VLMs, VLAs, or custom models, Exla reduces memory footprint by up to 80% and accelerates inference by 3–20x - all with just a few lines of code. https://cal.com/exla-ai/schedule
Founders
- Pranav Nair
Family Office Investors
Altss tracks family office allocations to YC-backed companies. Request access to see which family offices have invested in Exla.
See family office activityIndustry & Focus
B2BEngineering, Product and DesignArtificial IntelligenceEdge Computing SemiconductorsComputer Vision