co-serving

1 个项目 · ⭐ 19

llm-db/FineInfer

Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)

Python ⭐ 19 ⑂ 2 MIT · 2024-05-29推送

fine-tuning inference

2024-05-29