Publications

17 results at PyTorch Conference 2026

Beyond SPMD: Compiling Triton Kernels for Dataflow AI Architectures
- - Takuya Nakaike
  - Mori Ohara
- 2026
- PyTorch Conference 2026
Poster
Where the Blocks Live: Tier-Aware KV-Cache Routing for vLLM at Scale
- - Mengmei Ye
  - Bongwoo Bak
- 2026
- PyTorch Conference 2026
Poster
Real Shapes, Real Bugs: Model-Derived Operator Tests for Quick Out-of-Tree Accelerator Bring-Up
- - Kazuaki Ishizaki
  - Tuan Hoang Trong
  - et al.
- 2026
- PyTorch Conference 2026
Poster
Offloading KV Cache to Secondary Memory: A Three-Tier Hierarchy Emulator using vLLM
- - Chen Wang
  - Mengmei Ye
  - et al.
- 2026
- PyTorch Conference 2026
Poster
Enabling APC for hybrid models in vLLM
- - Stanisław Woźniak
  - Francesco Fusco
  - et al.
- 2026
- PyTorch Conference 2026
Poster
Train More with Less: Fewer GPUs, Less Data Movement, Better Cluster Utilization
- - Hyungyo Kim
  - Apoorve Mohan
  - et al.
- 2026
- PyTorch Conference 2026
Poster
Beyond the Execution Layer: Integrating Custom Accelerators with vLLM
- - Yannick Schnider
  - Sophie du Couédic
- 2026
- PyTorch Conference 2026
Poster