Shaoxun Zeng
where else to find them
website:https://shaoxunzeng.github.io/
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
all 7 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Weaver: Efficient Multi-LLM Serving with Attention Offloading | USENIX ATC '25 | 2025-07-07 |
Weaver implements attention offloading that lets hot models borrow KV cache memory on cold-model GPUs by shipping QKV vectors and running attention there… | ||
| SingularFS: A Billion-Scale Distributed File System Using a Single Metadata Server | USENIX ATC '23 | 2023-07-10 |
SingularFS builds a billion-scale distributed file system that uses a single metadata server and persistent memory with RDMA, replacing journaling with a KV… | ||
| nothing matches | ||