Lianmin Zheng
where else to find them
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- DMYTRO DZHULGAKOVonce
- Hao Zhangonce
- Ion Stoicaonce
all 15 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Panel Discussion: Training and Inference at Planet Scale | AI Infra Summit at PyTorch Conference 2025 | 2025-10-21 |
Panel covers concrete engineering moves: using five- or six-dimensional parallelism and mixture-of-experts sharding, splitting prefill vs decode into separate… | ||
| AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving | OSDI 2023 | 2023-07-10 |
AlpaServe uses model parallelism not just to fit big models but to statistically multiplex GPUs across many models, trading partition overhead for burst… | ||
| nothing matches | ||