Lowering the VRAM usage on NVDEC decoder #7387
Merged
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Outdated suggestions cannot be applied.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.
Changes
-threads 1
to NVDEC decoder explicitly since it doesn't implement threading support. The default number of threads in NVDEC reserves too much VRAM without actually using them.extra_hw_frames
workaround since it has been fixed by switching to yuv420p instead of nv12(disabling passthrough mode) in cuda pipeline. (save ~100MiB VRAM too)Issues
VRAM usage:
4k 10bit HEVC ->1080p H264
1474 MiB -> 712 MiB
1080p 10bit HEVC -> 1080p H264
491 MiB -> 293 MiB
observed by
nvidia-smi 511.79
on GTX 1650