mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
b85f2bc87d
This commit adds speculative support for parallel rendering across multiple GPUs. The parallelism is at the level of a session. Each session is given access to a different GPU. When all GPUs are busy, execution of the session will block until a GPU becomes available. The code is untested at the current time, and is being posted for comment. |
||
|---|---|---|
| .. | ||
| aa_nodes | ||
| app | ||
| backend | ||
| fixtures | ||
| inpainting | ||
| test_model_manager | ||
| test_model_probe/vae | ||
| __init__.py | ||
| conftest.py | ||
| dev_prompts.txt | ||
| legacy_tests.sh | ||
| test_config.py | ||
| test_item_storage_memory.py | ||
| test_model_probe.py | ||
| test_object_serializer_disk.py | ||
| test_path.py | ||
| test_profiler.py | ||
| test_sqlite_migrator.py | ||
| validate_pr_prompt.txt | ||