Julien Demouth
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 1 in the filters
on a stage with
never shared a talk
who talks about the same things
one talk is not yet a subject
| title | conference | date |
|---|---|---|
| Optimizing Large MoE Inference on NVIDIA Blackwell: NVFP4, ADP, and DualPipe Strat... | PyTorch Conference Europe 2026 | 2026-04-07 |
Describes moving MoE weights to NVFP4 to cut memory and keep accuracy on DeepSeek‑V3/R1, with FP4/FP8 KV caching to shrink attention state; NVFP4 uses… | ||
| nothing matches | ||