NVlabs/RocketKV

[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

⭐ 51 ⑂ 10 Python NOASSERTION · 2025-08-07推送

https://arxiv.org/abs/2502.14051

efficient-inference large-language-models pytorch transformers

51

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2025-08-07

最近推送

原文中文

暂无 README