←Backbytedance/ShadowKV0Copy as MarkdownView on GitHub↗306 stars·23 forks·Python·Apache-2.0·1 viewByteDance-Seed.github.io/ShadowKV↗ShadowKV[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference FeaturesAttention Optimization - Manages KV cache in shadows to boost throughput.