Conversation
Changes: throttle VRAM threshold checks to restore performance in high-layer-rate conditions.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review infoConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis pull request updates a single dependency constraint in 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Changes:
throttle VRAM threshold checks to restore performance in high-layer-rate conditions.
Merge the cuda VRAM consumption estimate with WDDM to mitigate lag in async allocator frees.
Example test conditions:
RTX 5090, PCIE5x16, Ryzen 9600 underclocked to 2GHz. Linux
Ace-step 1.5, 195s
Before:
After:
RTX5060, Windows WAN 2.1 608x400x81f
No arguments:
With --fast dynamic_vram: