InvokeAI/invokeai/app
Lincoln Stein b85f2bc87d add support for multi-gpu rendering
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.
2024-02-19 15:21:55 -05:00
..
api final tidying before marking PR as ready for review 2024-02-19 08:16:56 +11:00
assets/images tweaks in response to psychedelicious review of PR 2023-07-26 15:27:04 +10:00
invocations one more redundant RGB convert removed 2024-02-19 17:31:08 +11:00
services add support for multi-gpu rendering 2024-02-19 15:21:55 -05:00
shared tidy(nodes): move all field things to fields.py 2024-02-15 17:30:02 +11:00
util feat(nodes): update invocation context for mm2, update nodes model usage 2024-02-15 20:43:41 +11:00
api_app.py final tidying before marking PR as ready for review 2024-02-19 08:16:56 +11:00