Faster LLM Serving Startup with fastsafetensors
- 2026
- PyTorch Conference 2026
Talk
Publications
11 results at PyTorch Conference 2026
Inside the PyTorch Ambassador Model: How Ambassadors Grow PyTorch Adoption & How You Can Become One
- SAHDEV ZALA
- Sonny Mupfuni
- 2026
- PyTorch Conference 2026
TalkPortable Paged Attention: From Triton to Helion
- 2026
- PyTorch Conference 2026
TalkIntegrating the IBM Spyre accelerator
- David Grove
- Antoni Viros i Martin
- et al.
- 2026
- PyTorch Conference 2026
Talk2 in 1: Deep Dive into PyTorch Certified Associate (PTCA) and PyTorch Ambassador Program
- 2026
- PyTorch Conference 2026
PosterShape-Stable Dynamic Control Flow in PyTorch CUDA Graphs
- Daniel Galvez
- Thomas Bohnstingl
- 2026
- PyTorch Conference 2026
PosterBeyond the Execution Layer: Integrating Custom Accelerators with vLLM
- 2026
- PyTorch Conference 2026
PosterBeyond SPMD: Compiling Triton Kernels for Dataflow AI Architectures
- Takuya Nakaike
- Mori Ohara
- 2026
- PyTorch Conference 2026
PosterMAKCI: A Multi-Abstraction AI Kernel Cost Instrumentor for Performance Modeling in AI Compilers
- Shubham Jain
- Ritik Raj
- 2026
- PyTorch Conference 2026
PosterOffloading KV Cache to Secondary Memory: A Three-Tier Hierarchy Emulator using vLLM
- Chen Wang
- Mengmei Ye
- et al.
- 2026
- PyTorch Conference 2026
Poster