halexan

Could your please coded up a wrapper that removes a lot of the manual work in writing up a generic SinkhornTransformer encoder / decoder architecture. Thanks a lot! halexan

[Feature] DeepSeek-Coder-V2-Instruct-FP8 on 8xA100

6

### Motivation VLLM has announced their support for running llama3.1-405b-fp8 on 8xA100. This is the [blog](https://blog.vllm.ai/2024/07/23/llama31.html) Does sglang support running DeepSeek-Coder-V2-Instruct-FP8 on 8xA100? ### Related resources _No response_

BUG ChatTTS Internal Server Error

4

### Describe the bug ChatTTS部署成功，界面可以看到。  日志： 2024-07-04 00:42:25,572 xinference.model.utils 97 INFO Use model cache from a different hub. 2024-07-04 00:42:26,514 xinference.thirdparty.ChatTTS.core 16784 INFO Load from local: /root/.xinference/cache/ChatTTS 2024-07-04 00:42:27,649...