Parshant Sharma
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 2 in the filters
on a stage with
never shared a talk
who talks about the same things
- Aparna Ramani7 talks
- Kimish Patel2 talks
- Simon Mo7 talks
- Luca Antiga5 talks
- Merve Noyan11 talks
- Jana van Greunen2 talks
| title | conference | date |
|---|---|---|
| Inside MoE Optimization: A Profiler-Guided Tour of torch.compile and vLLM | DevConf.CZ 2026 | 2026-06-18 |
Shows a concrete pipeline that combines torch.compile + vLLM with hand‑written custom ops and CUDA graphs, yielding a fused MOE kernel that drops ~15–20 kernel… | ||
| Memory-Efficient AI: How PEFT and PyTorch Enable Accessible LLM Fine-Tuning | DevConf.IN 2026 | 2026-02-13 |
Full fine tuning of a 7B model needs roughly 112 GB of GPU RAM and multi‑GB checkpoints per task, while PEFT trains only 0.1–2% of parameters and cuts memory… | ||
| nothing matches | ||