ZML is building a high performance AI inference stack that’s built for production. Delivering peak performance on a wide range of chips and exceptional developer experience.
ZML is a production inference stack, purpose-built to decouple AI workloads from proprietary hardware. Any model, many hardware targets, one codebase, peak performance. Compiled directly to NVIDIA, AMD, TPU, Trainium for peak hardware performance on any accelerator. No rewriting.
Watch our video review: ZML Review: Peak Performance on Any Chip (NVIDIA, AMD, TPU & More)
Just released
LlamaIndex
LlamaParse is the most accurate agentic OCR platform for production AI — purpose-built for the documents agents actually encounter in the real world.
Reward (1.00 QUA)
Alchemy
Alchemy powers the blockchain infrastructure to accelerate the world's leading financial applications.
Reward (1.00 QUA)
Etherscan
Etherscan is the leading Blockchain Explorer, Search, API and Analytics Platform.
Reward (1.00 QUA)
Pebblely
Use AI to generate beautiful images of your products in different settings
Reward (1.00 QUA)