Burkhard Ringlein
where else to find them
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Jan van Lunterenonce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Portable High‑Performance LLM Serving: A Triton Backend for... | PyTorch Conference Europe 2026 | 2026-04-07 |
Introduces a Triton-only attention backend for vLLM that replaces hand‑written CUDA/HIP kernels and achieves cross‑vendor performance portability by autotuning… | ||
| How IBM Research Achieved vLLM Platform Portability with Triton Autotuning | Ray Summit 2024 | 2024-09-30 |
IBM Research replaces hand‑tuned CUDA kernels in vLLM with OpenAI Triton kernels plus an autotuning cache called Triton djaVu, which records best block‑size… | ||
| nothing matches | ||