CUDA Templates and Python DSLs for High-Performance Linear Algebra

Tile primitives for speedy kernels

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Deep learning at the speed of light.

[NeurIPS 2025] Geometry Aware Operator Transformer As An Efficient And Accurate Neural Surrogate For PDEs On Arbitrary Domains

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Discord bot to administer IITD Study Servers (unofficial)