24 au 26 février, 2027
Montréal, Canada
Half the Bits, All the Brains: LLM Quantization
The largest, smartest models are also the most expensive to run; quantization is one of the most accessible ways to cut that cost. This talk introduces model quantization technically, with a live pipeline demo: LLM Compressor handles quantization and sparsity, GuideLLM benchmarks latency and throughput against baseline, and lm-eval scores accuracy. Attendees leave with open source tools to compress their own models without losing performance.
Grace Ableidinger
Red Hat
Grace Ableidinger is an AI Developer Advocate at Red Hat based in NC. She is passionate about inference optimization, open-source software, and making AI sustainable and secure.
After graduating from NYU Tandon School of Engineering, studying CS, Math, and Game Dev, worked as a software engineer in the AI field before moving to Red Hat.
She has spoken at conferences (listed), produced technical content on Red Hat blog and YT, and IBM YT. She helps organize the official vLLM meetups.
