LEI WANG's picture

2 1 1

LEI WANG

yiakwy-xpu-team

·

https://yiakwy.github.io/

AI & ML interests

AI Chip Device Code Generation Stack : NVGPU CUDA SDK, AMDGPU ROCM SDK & GC IPU Poplar SDK

Recent Activity

published an article about 2 months ago

Efficient MoE Align & Sort design in SGLang Fused MoE

upvoted a paper about 1 year ago

SparQ Attention: Bandwidth-Efficient LLM Inference

new activity about 1 year ago

google/gemma-7b:Why the original GGUF is quite large ?

View all activity

Organizations

yiakwy-xpu-team's activity

New activity in google/gemma-7b about 1 year ago

Why the original GGUF is quite large ?

#11 opened about 1 year ago by

commented a paper over 1 year ago

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8, 2024 • 159 •