执行性能问题

#19

by fffff123 - opened 26 days ago

26 days ago

model(**inputs, return_dict=True).logits.view(-1, ).float() 这行代码执行会耗时很大，求教是啥原因呢，要2s左右了，怎么优化呢？
FlagEmbedding 、 Huggingface transformers、reranker with the ONNX files、reranker with infinity 这几种调用方式，性能有区别么

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment