Bin Yang
where else to find them
no profile links on file
what they talk about
all 5 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
- Wei Xue3×
- Weiguo Liu3×
- Dexun Chenonce
all 21 in the filters
who talks about the same things
- Chao Xie2 talks
- Jian He5 talks
- Clayton Coleman12 talks
- Dongdong Chen3 talks
- Xiao Zhang16 talks
- Sunyanan Choochotkaew8 talks
| title | conference | date |
|---|---|---|
| KV Cache: Accelerating AI Inference on Intel CPU | KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 | 2026-09-07 |
Serving LLM is bottlenecked by one scarce resource: HBM. The KV Cache grows with every token and every concurrent request, capping context length, throughput… | ||
| Full Lifecycle Data Analysis on a Large-scale and Leadership Supercomputer... | USENIX ATC 2024 | 2024-07-10 |
Six years of 40 TB over six years from Sunway TaihuLight (41,508 nodes) and bacon monitoring (deployed April 2017) analyze 6 million jobs totaling 4 billion… | ||
| HadaFS: A File System Bridging the Local and Shared Burst Buffer for Exascale | FAST '23: 21st USENIX Conference on File and Storage Technologies | 2023-02-21 |
HadaFS is a deployed burst-buffer file system that bridges local and shared BBs by implementing a Localized Triage Architecture to bind clients to selected… | ||
| AIC: Hosting Multiple Interactive Physical Clients on Single Computing Platform for IOT | Open Source Summit + Embedded Linux Conference North America 2019 | 2019-08-21 |
AIC runs multiple containerized Android instances on one Linux kernel using namespaces and cgroups, assigns dedicated devices (HDMI, USB cameras, touch) or… | ||
| End-to-end I/O Monitoring on a Leading Supercomputer | NSDI 2019 | 2019-02-26 |
Beacon implements end-to-end I/O tracing on the 40,960‑node Sunway TaihuLight, collecting per‑job traces from compute, forwarding, storage and metadata servers… | ||
| nothing matches | ||