FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
⭐ 2.8k
⑂ 206
Jupyter Notebook
Apache-2.0
· 2024-06-25推送
2.8k
Watchers
0
贡献者
0
Commits
0
Releases
57
Open Issues
2024-06-25
最近推送
原文
中文
暂无 README