Join Lagrange in expanding the boundaries of cryptographic research and its real-world applications.
We're delighted to introduce Christodoulos Pappasas, Sriram Sridhar, and Alireza Shirzad as Lagrange's 2025 interns.
DeepProve proved inference for Google’s Gemma3, unveiling a unified Einsum layer, optimized tensor commitments, and a distributed graph architecture that accelerates zkML at scale.
We're delighted to introduce Arthur Lazzaretti, Weijie Wang, and Hadas Zeilberger as Lagrange's 2024 interns.
DeepProve gained the ability to prove full-sequence (1024 token) inference for GPT-2 on the same benchmark hardware used in prior 10-token runs.
DeepProve’s capabilities were expanded to support full inference proofs for transformer-based large language models, culminating in the successful proof of inference for OpenAI’s GPT-2.
