Add adaptive memory management based on system RAM#4
Open
sb1992 wants to merge 1 commit into
Open
Conversation
- Auto-detect system RAM and set MLX buffer cache limit accordingly: 8 GB → 0 cache, 16 GB → 1.6 GB, 24 GB → 4.8 GB, 32+ GB → 8 GB (cap) - Add --cache-gb CLI override for manual tuning - Add --num_frames flag to control chunk size (lower = less memory) - Clear MLX cache between denoising chunks to prevent runaway growth - Free Whisper encoder and face detector after preprocessing - Add memory profiling script (scripts/profile_memory.py) - Update README with memory optimization docs and benchmark table Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
min(8, max(0, (ram_gb - 12) * 0.4))GB — reserves 12 GB for OS, caps at 8 GB--cache-gbCLI override and--num_framesflag for manual tuningMemory benchmarks (v1.5, 256px)
Test plan
--cache-gb 0, verify ~10.5 GB peak--cache-gb 8, verify no regression vs. unlimited🤖 Generated with Claude Code