← Search

Sanket Purandare

2 accepted papers

2025

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond

ICLR 2025poster

While transformers have been at the core of most recent advancements in sequence generative models, their computational cost remains quadratic in sequence length. Several subquadratic architectures have been proposed to address this computational issue. Some of them, including long convolution seque…

Cited by 0SourcePDFScholar
2025

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

ICLR 2025poster

The development of large language models (LLMs) has been instrumental in advancing state-of-the-art natural language processing applications. Training LLMs with billions of parameters and trillions of tokens requires sophisticated distributed systems that enable composing and comparing several state…