GitHub - punica-ai/punica: Serving multiple LoRA finetuned L

Serving multiple LoRA finetuned LLM as one. Contribute to punica-ai/punica development by creating an account on GitHub.

Related Keywords

Danyang Zhuo , Lequn Chen , Yongji Wu , Luis Ceze , Arvind Krishnamurthy , , Segmented Gather Matrix Vector , Huggingface Transformers ,