Michael Yuan

Conf42: Large Language Models (LLMs) 2024

Self-hosted LLMs across all your devices and GPUs

Fast and Portable Llama2 Inference on the Heterogeneous Edge: An alternative to Python. Compared with Python, Rust+Wasm apps could be 1/100 of the size, 100 times the speed, and, most importantly, securely run everywhere at full hardware acceleration without any change to the binary code.