Yibo Zhu
where else to find them
no profile links on file
what they talk about
all 8 in the filters
where they keep going back
- NSDI2 editions2019–2023
all 5 in the filters
on a stage with
all 55 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Optimizing RLHF Training for Large Language Models with Stage Fusion | NSDI '25 | 2025-04-28 |
RLHFuse claims up to 3.7× end-to-end RLHF training throughput by splitting tasks into sample-level subtasks and microbatch subtasks. It overlaps generation and… | ||
| DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language... | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
System disaggregates prefill and decoding onto separate GPUs, assigns independent parallelism and resource plans for each phase, and places instances to cut… | ||
| BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing | NSDI 2023 | 2023-04-17 |
Distributed GNN training system BGL builds a dynamic cache engine and a two-level CPU+GPU cache that together cut feature-retrieval traffic and reduce… | ||
| Collie: Finding Performance Anomalies in RDMA Subsystems | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
Collie systematically searches RDMA workload space using simulated annealing guided by hardware performance and diagnostic counters to drive tests toward… | ||
| FreeFlow: Software-based Virtual RDMA Networking for Containerized Clouds | NSDI 2019 | 2019-02-26 |
FreeFlow implements a software RDMA virtualization layer that runs on commodity RDMA NICs, intercepting libibverbs’ serialized commands and presenting shadow… | ||
| dShark: A General, Easy to Program and Scalable Framework for Analyzing In-network | NSDI 2019 | 2019-02-26 |
dShark provides a MapReduce-like pipeline that parses mirrored packets into compact summaries using a JSON declarative spec and runs per-group analysis with… | ||
| Slim: OS Kernel Support for a Low-Overhead Container Overlay Network | NSDI 2019 | 2019-02-26 |
Slim implements connection-based virtualization that maps virtual container connections to host TCP connections via a user-space Slim router, avoiding… | ||
| Tiresias: A GPU Cluster Manager for Distributed Deep Learning | NSDI 2019 | 2019-02-26 |
Tiresias is a GPU cluster manager that actually implements two age‑based schedulers — Discretized Two‑Dimensional Gittins index (needs a prior distribution)… | ||
| 007: Democratically Finding the Cause of Packet Drops | NSDI '18 | 2018-04-09 |
007 is a host-only deployment that diagnoses per-TCP packet loss by subscribing to retransmission events, issuing one traceroute per retransmitting flow, and… | ||
| nothing matches | ||