VILA is a visual language model (VLM) pre-trained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge.

We enable LLMs to work on infinite-length texts without compromising efficiency and performance.

Low-bit weight-only quantization for LLMs.

LongLoRA takes advantage of shifted sparse attention to greatly reduce the finetuning cost of long context LLMs.

This TinyML project aims to enable efficient AI computing on the edge by innovating model compression techniques as well as high-performance system design.

This project introduce PockEngine: a tiny, sparse and efficient engine to enable fine-tuning on various edge devices. PockEngine supports sparse backpropagation: it prunes the backward graph and sparsely updates the model with measured memory saving and latency reduction while maintaining the model quality.