SWivid/F5-TTS
Vedi su GitHubMy RTF is always around 0.12 with TRT-LLM docker on L20, never match the claimed benchmark result
Open
#1214 aperta il 10 nov 2025
documentationenhancementhelp wanted
Metriche repository
- Star
- (14.687 star)
- Metriche merge PR
- (Metriche PR in attesa)
Descrizione
Checks
- This template is only for usage issues encountered.
- I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
- I have searched for existing issues, including closed ones, and couldn't find a solution.
- I am using English to submit this issue to facilitate community communication.
Environment Details
nvidia L20, soar97/triton-f5-tts:24.12, just as https://github.com/SWivid/F5-TTS/blob/main/src/f5_tts/runtime/triton_trtllm/README.md
But my RTF is always around 0.12
⚡ Real-Time Factor:
Mean: 0.120x
Median: 0.112x
Min/Max: 0.097x / 0.152x
My result is much slower than the claimed benchmark result.
What did I do wrongly ?
Steps to Reproduce
- find a clean L20 machine, clone the project
- start the triton docker
MODEL=F5TTS_v1_Base docker compose upas https://github.com/SWivid/F5-TTS/blob/main/src/f5_tts/runtime/triton_trtllm/README.md said - test the RTF
✔️ Expected Behavior
No response
❌ Actual Behavior
No response