Apply Inference Optimizations

Apply FlashDreams-style inference speedups to model integrations after a baseline exists: bounded windows and fixed K/V caches, cache/decode overlap, `torch.compile`, CUDA graph capture, attention backend checks, decoder layout or replacement, transfer/materialization changes, and ordered presentation tuning. Use when porting known optimizations into a runner, demo, serving adapter, or downstream integration while preserving quality and reset behavior.

NVIDIA Updated 23k repo stars
FlashDreams

File contents

nvidia/flashdreams commit 6fbd3131b2

Frequently asked questions

npx get-skill add nvidia/apply-inference-optimizations