lllyasviel / lllyasviel/stable-diffusion-webui-forge
Models caching does not work (sd_checkpoints_limit)
Open
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Tested setting `sd_checkpoints_keep_in_cpu: false, sd_checkpoints_limit: 3, sd_checkpoint_cache: 3`. Nothing worked. Every request for a new model is long.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported configuration with sd_checkpoints_keep_in_cpu set to false, sd_checkpoints_limit set to 3, and sd_checkpoint_cache set to 3. Trace the model-loading and caching path to determine why a new model request remains slow; done means the configured cache limits are respected and repeated requests avoid unnecessary long reloads.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100