G.O.D
G.O.D
1. make `use_reentrant=True` explicit, because it will default to true if it is not assigned 2. fix gradient checkpoint when it used with dropout turned on. if `preserve_rng_state=False`, the dropout...
assume one flop equals two macs
**Describe the bug** The op fails to launch when using Ray, but runs successfully with torchrun. **To Reproduce** ``` import sys from typing import Optional import ray import torch import...
We can apply the DPM solver to flow-matching models almost out of the box. [This demo](https://github.com/gameofdimension/dpm-flow-match) shows how to use DPM on Flux.1-dev—hope it helps!