How to support multiple tts request meanwhile when using 1 worker?

[dawenxi-only]

Self Checks

• I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find any relevant information that meets my needs. English 中文 日本語 Portuguese (Brazil)
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell us your story.

I start a tts service with 1 worker. When I post the tts service with 1 reqeust, the service run normal.But when I post the tts service with 2 reqeust, the service raise error.

RuntimeError: CUDA error: device-side assert triggered
| CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
| For debugging consider passing CUDA_LAUNCH_BLOCKING=1
| Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

2. What is your suggested solution?

I guess that some global variable cause this. I want to know how to fix this, thanks.

3. Additional context or comments

No response

4. Can you help us with this feature?

• I am interested in contributing to this feature.

[Stardust-minus]

No support plan.