Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

aider: Fixed CPU memory issues by deleting large objects and forcing garbage collection.

Browse Source 
# 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
```
This commit is contained in:
Brandon Rising 2024-05-28 15:05:36 -04:00
parent 46950a9bd0
commit e68c49167a
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
View File

@ -32,8 +32,10 @@ def convert_ldm_vae_to_diffusers(
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)
torch.cuda.empty_cache()
if dump_path:
vae.save_pretrained(dump_path, safe_serialization=True)
@ -55,8 +57,10 @@ def convert_ckpt_to_diffusers(
"""
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)
torch.cuda.empty_cache()
# TO DO: save correct repo variant
if dump_path:
@ -80,8 +84,10 @@ def convert_controlnet_to_diffusers(
"""
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)
torch.cuda.empty_cache()
# TO DO: save correct repo variant
if dump_path: