Qizhen Weng
where else to find them
github:qzweng
linkedin:qizhen-weng
what they talk about
all 5 in the filters
where they keep going back
no series more than once — all 4 in the filters
on a stage with
all 35 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Toppings: CPU-Assisted, Rank-Aware Adapter Serving for LLM Inference | USENIX ATC '25 | 2025-07-07 |
System pins the base LLM on GPUs and dynamically loads LoRA adapters from host memory, while CPU-assisted LoRA computation precomputes the lightweight XAB… | ||
| GPU-Disaggregated Serving for Deep Learning Recommendation Models at Scale | NSDI '25 | 2025-04-28 |
Prism disaggregates CPU and GPU pools via graph-level partitioning and RDMA so embedding lookups run on CPU nodes and dense nets on GPU nodes, using a fusgraph… | ||
| Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation... | USENIX ATC '23 | 2023-07-10 |
Paper defines a statistical fragmentation metric that predicts expected unallocatable GPU capacity given task distributions, implements a scheduler called… | ||
| MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU... | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
A two-month Alibaba MLaaS trace covers over 6,700 GPUs across ~1,800 nodes with 1.2M tasks, 7.5M instances and shows concrete pain points: 85% gang-scheduled… | ||
| nothing matches | ||