vLLM Conference Set for August with Speakers from NVIDIA and Meta
vllm_project · x · 2026-08-05
The vLLM project announced its upcoming AI inference conference taking place August 24–26 in San Francisco. The event will gather key builders from NVIDIA, AMD, Google TPU, Meta, and PyTorch to deep dive into the latest accelerator technologies, training and serving pipelines, and production-scale inference optimizations.
Related event: vLLM Announces Inaugural AI Inference Summit in San Francisco for August(2 posts)→
More from Infra
- Ex-Jane Street Exec Explains How They Cut Trading System Latency by 100x — ivan_bezdomny · 2026-08-05
- DeepGrove Releases On-Device LLM Running at 200+ tokens/s on Mac Mini — ycombinator · 2026-08-05
- Musk: AI and Robotics Will Trigger Unprecedented Global Bandwidth Demand — XFreeze · 2026-08-05
- AMD CEO Lisa Su Raises Revenue and EPS Targets, Citing Above-Market Growth — firstadopter · 2026-08-05
- Ying Sheng on SGLang's Evolution and Founding RadixArk After xAI — xiaosun86 · 2026-08-05
- MiniMax H3 Runs Offline on MacBooks and Gaming GPUs for Free — cocktailpeanut · 2026-08-05