Berkeley, CA

Shuo Yang

Advanced
@andy-yang-1

EECS PhD at UC Berkeley; @lm-sys member

andy-yang-1.github.io/

DoubleSparse. 16-fold memory access reduction with nearly no loss

107

flash-fp32. Fast FP32 operations with half-precision decomposition

2

FastChat. The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

1

cheap-trick. sgemm optimization

1

Sparse-VideoGen. [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

1

sglang. SGLang is a fast serving framework for large language models and vision language models.

1
6
Apply