diT

Tag

Cards List
#diT

@RisingSayak: Tensor parallel loading in Diffusers got a massive upgrade On Flux.2-Dev DiT, with a TP degree of 4 (A10G): • 30.4s → 1…

X AI KOLs Following ↗ · 2026-10-01 Cached

Hugging Face Diffusers 上张量并行(tensor parallel)加载迎来重大优化:在 Flux.2-Dev DiT、TP=4(A10G)配置下,加载时间从 30.4s 降至 12.5s(约 2.4 倍提速),每 rank 峰值 CPU 内存从 64.1 GB 降至 6.8 GB(减少约 89%)。相关分布式推理(Accelerate 与 PyTorch Distributed)用法已更新到官方文档。

0 favorites 0 likes
← Back to home

Submit Feedback