Jiaxin Wang#
Jiaxin Wang is a member of the AMD Quark team, where she specializes in model compression and deployment for AI inference frameworks such as vLLM and SGLang. Her work spans post-training quantization, performance benchmarking, and evaluation of state-of-the-art open-source foundation models, with a focus on optimizing inference efficiency while maintaining model accuracy across diverse deployment backends.
Posts by Jiaxin Wang
