AMD AI DevDay Paris on Dec 12: vLLM Maintainer to Talk Decode Optimization, Free ROCm Cert

AccBalanced · x · 2026-11-21

AMD AI DevDay Paris takes place Dec 12, 9:00–18:00 CET at Station F, free with hands-on workshops and an ROCm certification track. vLLM maintainer Tun Jian Tan (Embedded LLM) will present MonoKernel decode, KV-cache reuse, and prefill/decode separation; Hugging Face ML engineer Abdennacer Badaoui will cover running open models efficiently on AMD GPUs. Capacity is limited.

Original post →

More from Companies & People

Companies & People channel →