Invited Talk

OpenXLA Summer DevLab 2026 — Benchmarking vLLM on XLA Backends

Invited talk at Google OpenXLA DevLab Summer 2026 on "Benchmarking vLLM on XLA Backends: From CUDA to OpenXLA for LLM Serving", speaking alongside engineers from Google, NVIDIA, …

Rabimba Karanjai

• Jun 25, 2026 • 2 min read

Read more