Is your feature request related to a problem?
Celery latency is too high for near-real-time use cases such as STT, TTS, and S2S. This causes delays and impacts performance for critical applications.
Describe the solution you'd like
- Achieve fast responses without scaling out ECS
- Maintain resources within AWS billing limits
- Optimize latency for real-time use cases
Original issue
Describe the current behavior
Celery latency is too high for near-real time use cases (STT,TTS,S2S).
Describe the enhancement you'd like
Fast responses without ECS being scaled out thereby causing us to increase resources.
Why is this enhancement needed?
Optimal latency for realtime usecases and AWS bill under limit.
Additional context
Add any other context, metrics, screenshots, or examples about the enhancement here.
Celery Optmizations
Is your feature request related to a problem?
Celery latency is too high for near-real-time use cases such as STT, TTS, and S2S. This causes delays and impacts performance for critical applications.
Describe the solution you'd like
Original issue
Describe the current behavior
Celery latency is too high for near-real time use cases (STT,TTS,S2S).
Describe the enhancement you'd like
Fast responses without ECS being scaled out thereby causing us to increase resources.
Why is this enhancement needed?
Optimal latency for realtime usecases and AWS bill under limit.
Additional context
Add any other context, metrics, screenshots, or examples about the enhancement here.
Celery Optmizations