Zhang's picture

1

Zhang

Minjia

·

https://minjiazhang.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 3 days ago

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

authored a paper 3 days ago

DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies

authored a paper 3 days ago

ZeRO-Offload: Democratizing Billion-Scale Model Training

View all activity

Organizations

Articles 1

Article

43

Bamba: Inference-Efficient Hybrid Mamba2 Model

Papers 16

arxiv:2412.18619

arxiv:2408.00727

arxiv:2407.08454

arxiv:2407.05282

models

None public yet

datasets

None public yet