Ron Kahn
where else to find them
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Ekin Karabulutonce
who talks about the same things
- Brandon Kang4 talks
- Ekin Karabulut2 talks
- Mofi Rahman16 talks
- Ricardo Aravena25 talks
- Yuan Tang23 talks
- Abdel Sghiouar29 talks
| title | conference | date |
|---|---|---|
| Beyond the Theory: What Actually Breaks When You Scale Your Disaggregat... | PyTorch Conference Europe 2026 | 2026-04-07 |
Disaggregated inference runs vLLM and SGLang on Kubernetes with Dynamo or LLMD, Kai for scheduling, and Grove or leader-worker-set for workload APIs, and… | ||
| Lightning Talk: My Job Says 'Running' but Nothing's Running: Kubernetes Status Reality... | Cloud Native + Kubernetes AI Day North America 2025 | 2025-11-10 |
Kubernetes often reports a distributed PyTorch/MPI job as Running while no training progresses because Kubernetes only validates per-pod readiness probes and… | ||
| nothing matches | ||