PyTorch ATX: The Future of Inferencing

Description

Join PyTorch ATX this August for a hands-on look at the next generation of AI inference pipelines. We’ll explore the full modern stack—from aggressive model-size reductions like INT4/INT8 quantization and pruning, dynamic batching, paged-attention memory tricks, and multi-node scheduling. We'll dive into vLLM—today’s most popular open-source engine for high-throughput LLM inference—alongside other cutting edge inference stacks.

Expect deeply technical talks, live demos, and open Q&A with the engineers building and running these systems.

Presentations

• TBD

When: August 2025 - exact date TBD
Where: Austin, TX - exact location TBD

Food and beverages will be provided.