Jiaming Tang

Jiaming Tang is a Ph.D. student at MIT EECS, advised by Prof. Song Han, where his research focuses on efficient algorithms and systems for large language models. He is best known for AWQ (Activation-aware Weight Quantization), which received the Best Paper Award at MLSys 2024 and has been integrated into multiple inference frameworks including Transformers, vLLM, and TensorRT-LLM. His work also includes Quest for query-aware long-context LLM inference and contributions to efficient vision-language model deployment.