Added command line argument --not_on_device to disable perform_everything_on_device during inference.#2980
Merged
FabianIsensee merged 2 commits intoMIC-DKFZ:masterfrom Mar 13, 2026
Conversation
…ume on cuda device Enabling this feature ensures sliding window aggregation is performed on cpu. This feature is usefull for inference on GPUs without enough VRAM (e.g. CTs with more than 1000 slices might not fit in 8GB VRAM)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
--not_on_deviceensures sliding window aggregation is performed on cpu.perform_everything_on_device=True) and falls back to the CPU device only after failure (which might take some time). Moreover, the gaussian heatmap remains allocated on the CUDA device due to the lru_cache.