Amber-Believe

Annotations will bounce forward：标注内容会出现前移

1

**Describe the bug** When Relation Extraction is used for annotation, annotation content will move forward when the mouse is released, for example: start: 3, end:5, and then the annotation becomes...

[Performance]: V0.6.0 version of the model, benchmarking found that the number of successful responses accounted for half of the number of requests, which is why

4

### Proposal to improve performance _No response_ ### Report of performance regression _No response_ ### Misc discussion on performance _No response_ ### Your current environment (if you think it is...

[Bug]对VLM来说，是否支持多个lora adapter使用

5

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version....

[Bug] 更改session_len无法解决输出截断的问题

2

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

模型训练，使用的是哪一方的资源

9

### Question Category Others ### Installation Source Source ### Secretflow Version 1.10.0b1 ### Operating System and Distribution Ubuntu 22.04.3 ### Python Version Python 3.10.15 ### Bazel Version _No response_ ###...

是否支持多模态的多lora推理

2

### Motivation 对不同领域都微调了一个lora adapter（基于qwen2.5-vl-7b）,这个时候就希望，在显存不猛增的情况下，灵活地动态更改模型，也就是需要推理框架支持多lora推理，可以切换 adapter，**当前我们的服务是否支持，或者未来会支持吗** ### Related resources vllm有提供这个 https://docs.vllm.ai/en/latest/features/lora.html#serving-lora-adapters ### Additional context _No response_