
Darmstadt, Germany, 16 November 2026 – Daisytuner, the Darmstadt-based team automating performance engineering for AI models across different chips, has raised €6 million in Seed funding and launched Daisyflow, its inference engine for running AI models efficiently on any hardware. We co-led the round with Elaia, with participation from Amadeus Capital Partners, Apex Ventures and Seedcamp, and have backed the team since day one.
The new bottleneck: tuning models to chips
Open-weight models are now strong enough for companies to run state-of-the-art AI on their own hardware. As AI agents multiply the compute each task requires, what decides the cost and speed of AI is increasingly how well a model runs on the chip underneath. Yet performance engineering is still largely manual work, concentrated in a handful of frontier labs and focused on the latest hardware generation. Every new model or chip can break yesterday’s optimisations, and most hardware ends up running well below its potential.
Daisyflow: one engine for any chip
Daisytuner automates this work. Its open-source compiler turns code from frameworks such as PyTorch into native code for each chip, from Nvidia and AMD GPUs to next-generation architectures. AI agents test optimisations on real hardware around the clock, and the compiler verifies that each one is correct before it is used. Verified optimisations are stored and reused on similar code, so every new workload makes the next one faster.
Daisyflow brings this into production inside the customer’s own infrastructure, serving language, vision, speech and recommendation models through the APIs teams already use. According to Daisytuner, first results show Qwen 2.5 running up to 18% faster than vLLM on AMD Instinct GPUs.
Where Daisytuner goes next
Daisytuner will use the funding to bring Daisyflow to more enterprises, grow its team and expand its compiler technology.
“Demand for AI compute is growing faster than any one chip generation can serve. The hardware to meet it is already out there, from established GPUs to a wave of new accelerators, but software keeps much of it on the sidelines. We’re working with chip vendors, European hyperscalers and enterprises to change that, so every chip runs at full speed and new ones go into production the moment they arrive,” says Lukas Trümper, CEO and co-founder of Daisytuner.
About Daisytuner
Founded in 2024 by Lukas Trümper and Adrian Schmitz, Daisytuner builds on over a decade of research. The team comes from leading research labs including ETH Zurich, TU Munich, RWTH Aachen, TU Darmstadt and Lawrence Livermore National Laboratory.
worth solving?