mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
e68c49167a
# Aider chat conversation:
USER: `invokeai/backend/model_manager/convert_ckpt_to_diffusers.py` Im having issues with cpu memory, not gpu memory
ASSISTANT: To address CPU memory issues, we can make the following changes:
1. Use `del` to explicitly delete large objects when they are no longer needed.
2. Use `gc.collect()` to force garbage collection after deleting large objects.
Here are the *SEARCH/REPLACE* blocks:
invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
vae = AutoencoderKL(**vae_config)
with torch.no_grad():
vae.load_state_dict(converted_vae_checkpoint)
vae.to(precision)
torch.cuda.empty_cache()
=======
vae = AutoencoderKL(**vae_config)
with torch.no_grad():
vae.load_state_dict(converted_vae_checkpoint)
del converted_vae_checkpoint # Free memory
import gc
gc.collect()
vae.to(precision)
>>>>>>> REPLACE
```
invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
pipe = download_from_original_stable_diffusion_ckpt(Path(checkpoint_path).as_posix(), **kwargs)
with torch.no_grad():
pipe = pipe.to(precision)
torch.cuda.empty_cache()
=======
pipe = download_from_original_stable_diffusion_ckpt(Path(checkpoint_path).as_posix(), **kwargs)
with torch.no_grad():
del kwargs # Free memory
import gc
gc.collect()
pipe = pipe.to(precision)
>>>>>>> REPLACE
```
invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
pipe = download_controlnet_from_original_ckpt(checkpoint_path.as_posix(), **kwargs)
with torch.no_grad():
pipe = pipe.to(precision)
torch.cuda.empty_cache()
=======
pipe = download_controlnet_from_original_ckpt(checkpoint_path.as_posix(), **kwargs)
with torch.no_grad():
del kwargs # Free memory
import gc
gc.collect()
pipe = pipe.to(precision)
>>>>>>> REPLACE
```
|
||
|---|---|---|
| .. | ||
| app | ||
| assets | ||
| backend | ||
| configs | ||
| frontend | ||
| invocation_api | ||
| version | ||
| __init__.py | ||