Stephanie Wang
where else to find them
no profile links on file
what they talk about
all 9 in the filters
where they keep going back
- Ray Summit3 editions2020–2024
all 7 in the filters
on a stage with
all 25 in the filters
who talks about the same things
- Robert Nishihara11 talks
- Jules S. Damji7 talks
- Ion Stoica40 talks
- Antoni Baum3 talks
- (unnamed presenter)4 talks
- Hui Lei4 talks
| title | conference | date |
|---|---|---|
| NanoFlow: Towards Optimal Large Language Model Serving Throughput | OSDI '25 | 2025-07-07 |
NanoFlow splits request batches into nano-batches and duplicates per-batch operations to overlap compute, memory (KV cache), and network work within a single… | ||
| Evolving Ray Core: Scalability, Reliability, and Compiled Graphs | Ray Summit 2024 | 2024-09-30 |
Weekly releases and structured logging reduce release latency and improve observability, streaming generators let callers consume object refs while tasks still… | ||
| ExoFlow: A Universal Workflow System for Exactly-Once DAGs | OSDI 2023 | 2023-07-10 |
ExoFlow implements a workflow runtime that decouples execution from recovery, providing exactly-once semantics via a separate recovery layer, task annotations… | ||
| One beginner’s guide to XR world building | XConf North America 2022 | 2022-07-27 |
Built an AR book with Unity and Vuforia using hand drawings turned into five‑star image targets, Unity Asset Store models, a few lines of C# and export via… | ||
| Ray Internals: Object Management with the Ownership Model | Ray Summit 2021 | 2021-06-22 |
Ray restructures object metadata by shards the master across workers so the creator of an object owns its metadata, keeping location and lineage local to… | ||
| Ownership: A Distributed Futures System for Fine-Grained Tasks | NSDI ’21 | 2021-04-12 |
Ownership claims a decentralized runtime that shards metadata by object owner, trades global persistence for simple recovery, and achieves 1ms latency per task… | ||
| Taming Java Dependencies in 70+ GCP Client Libraries | Devnexus 2021 | 2021-02-17 |
Google Cloud manages 70+ Java client libraries, each with 20+ direct dependencies, by publishing a centralized google cloud share dependencies bom and using… | ||
| Ray Internals: A Peek at `ray.get` | Ray Summit 2020 | 2020-09-30 |
Deep dive into what ray.get actually does: precise lifecycle of an object, how small objects stay at the owner while large objects live in a distributed store… | ||
| Ray: A distributed system for emerging AI applications | Strange Loop 2018 | 2018-09-26 |
Ray is an open source distributed system that implements task and actor abstractions for Python ML workloads, with a C++ backend, Python workers, an in‑memory… | ||
| nothing matches | ||