Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact.
In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code.
Read more:
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
Cheaper inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → on open biology models widens who can run structure prediction, drug design, and mutation-effect tools, and the released optimization code is a reusable template for AI-assisted GPU kernel writing.
