abetlen / abetlen/llama-cpp-python
Increase server timeout for long requests
Open
enhancement
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 1.4k
- PR merge metrics
- PR metrics pending
Description
While operating on the CPU, I am able to observe both the request and completion logs. However, due to the time-consuming nature of the request, the server issues a 504 timeout error before the completion is finalized. Therefore, I kindly propose the inclusion of an ENV variable or a flag that would allow for the adjustment of the server timeout duration.
Contributor guide
Assessment
This issue has not been assessed yet.