SangBin Cho
where else to find them
no profile links on file
what they talk about
all 6 in the filters
where they keep going back
- Ray Summit3 editions2020–2024
on a stage with
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| The Evolution of Multi-GPU Inference in vLLM | Ray Summit 2024 | 2024-09-30 |
vLLM shards 405B-class models across GPUs using tensor + pipeline parallelism, rearchitects the control plane to use Ray compiled graph with GPU RDMA and Niel… | ||
| Data Processing on Ray | Ray Summit 2021 | 2021-06-22 |
Ray adds concrete features to run large-scale ETL and ETL→ML pipelines: it implements memory-aware scheduling and locality-aware placement to avoid needless… | ||
| Data Processing on Ray | PyCon US 2021 | 2021-05-14 |
Ray adds concrete systems work: locality-aware scheduling and admission control so tasks aren’t placed where inputs won’t fit; a decentralized memory manager… | ||
| Debugging and Observability for Distributed Ray Applications | Ray Summit 2020 | 2020-09-30 |
Describes concrete debugging and observability features added to Ray: a memory view that shows object references and call sites, custom metrics recorded via a… | ||
| nothing matches | ||