Jason Ansel
where else to find them
what they talk about
where they keep going back
- PyTorch Conference3 editions2022–2025
on a stage with
- Dunfan Luonce
who talks about the same things
- Elias Ellison3 talks
- Jana van Greunen2 talks
- Christian Keller5 talks
- Luca Antiga5 talks
- Mark Saroufim5 talks
- Michael Lazos2 talks
| title | conference | date |
|---|---|---|
| Helion's New CuTe DSL and Pallas Backends and How We Built Them Via Agents | KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 | 2026-09-07 |
Helion adds two new backends: a CuteDSL backend targeting NVIDIA Blackwell and a Pallas TPU lowering that emits VM-prefetched pipelines. Autotuner chooses… | ||
| Helion: A High-level DSL for Kernel Authoring | PyTorch Conference 2025 | 2025-10-22 |
A Python-embedded DSL that compiles to Triton, Helion exposes a single critical construct hl.tile tiling construct and maps inner tile bodies to device kernels… | ||
| A Halide Backend for TorchInductor | PyTorch Conference 2024 | 2024-09-18 |
A Halide backend is added to TorchInductor as a reference backend that targets extensibility for kernel‑level DSLs and hardware vendors, integrated with… | ||
| PyTorch 2.0: TorchInductor | PyTorch Conference 2022 | 2022-12-02 |
TorchInductor is a PyTorch-native compiler backend written in Python that maps PyTorch models into generated Triton kernels on NVIDIA GPUs and C++/OpenMP on… | ||
| nothing matches | ||