HeyGen x Google Cloud: Bringing Avatar IV to TPUs

T1Covered by 1 source · first reported by Google — The Keyword / AI / Research / DeepMind / Developers at 24 Sept, 11:50 UTC

HeyGen ported their 18B+ parameter Avatar IV video generation model to Google Cloud's Trillium (v6e) TPUs via torchax and XLA, utilizing FSDP and Ulysses sequence parallelism across an eight-chip mesh. To achieve a 1.86x speedup for real-time streaming, the engineering team pipelined exposed…

cloud hardware

Sources

T1HeyGen x Google Cloud: Bringing Avatar IV to TPUsGoogle — The Keyword / AI / Research / DeepMind / Developers24 Sept, 11:50