Anca Agape
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Andre Darabanovonce
who talks about the same things
- Ayichew Hailu4 talks
- Maude Lemaire7 talks
- Wilfred Spiegelenburg6 talks
- Yun Jin3 talks
- Wei Huang17 talks
- Da Ma11 talks
| title | conference | date |
|---|---|---|
| Gang Scheduling for Llama | @Scale: Systems & Reliability 2025 | 2025-05-06 |
Llama 4 uses a MoE design with >2 trillion parameters but only activates ~17B for Maverick, forcing distributed inference. Twine implements gang scheduling to… | ||
| Live Q&A Session – Anca Agape | Systems @Scale Winter 2022 | 2022-12-07 |
Q&A lists concrete practices and hard lessons: use the utilization saturation errors metrics to get cost‑per‑request; prefer queues for command buffering and… | ||
| Live Q&A Session #1 | Reliability @Scale Summer 2022 | 2022-08-31 |
Panel answers specific operational questions about outages and prevention: how automatic P0 paging fires when control‑plane/API or global traffic drops and… | ||
| nothing matches | ||