Julien Demouth
Employers on the program
- 2026NVIDIA1 talk
Events1
Conferences1
Talks1
Years active2026
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- PyTorch Conference
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Apr 7, 2026 | PyTorch Conference Europe 2026 | PyTorch Conference | speaker | Optimizing Large MoE Inference on NVIDIA Blackwell: NVFP4, ADP, and DualPipe Strategies as NVIDIA Deploying massive Mixture-of-Experts (MoE) architectures like DeepSeek-V3/R1 requires a co-designed approach leveraging NVIDIA Blackwell’s fifth-generation…Show lessDeploying massive Mixture-of-Experts (MoE) architectures like DeepSeek-V3/R1 requires a co-designed approach leveraging NVIDIA Blackwell’s fifth-generation Tensor Cores. This session details the transition to NVFP4 precision for MoE weights to significantly reduce memory load, coupled with FP4/FP8... |
Frequent co-speakers
No one else spoke at two or more of the same events.
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.