da8916f926
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead |
||
---|---|---|
.. | ||
scripts | ||
ldsr_model_arch.py | ||
preload.py | ||
sd_hijack_autoencoder.py | ||
sd_hijack_ddpm_v1.py | ||
vqvae_quantize.py |
da8916f926
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead |
||
---|---|---|
.. | ||
scripts | ||
ldsr_model_arch.py | ||
preload.py | ||
sd_hijack_autoencoder.py | ||
sd_hijack_ddpm_v1.py | ||
vqvae_quantize.py |