SWivid/F5-TTS

My RTF is always around 0.12 with TRT-LLM docker on L20, never match the claimed benchmark result

Open

#1,214 opened on Nov 10, 2025

View on GitHub
 (29 comments) (1 reaction) (0 assignees)Python (2,149 forks)github user discovery
documentationenhancementhelp wanted

Repository metrics

Stars
 (14,687 stars)
PR merge metrics
 (PR metrics pending)

Description

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

  1. find a clean L20 machine, clone the project
  2. start the triton docker MODEL=F5TTS_v1_Base docker compose up as https://github.com/SWivid/F5-TTS/blob/main/src/f5_tts/runtime/triton_trtllm/README.md said
  3. test the RTF

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Contributor guide

Research direction
Compare the user's Docker setup with the benchmark environment: verify GPU driver version, TensorRT LLM version, and container launch flags (e.g., gpus all, shared memory size). Check if the model is using FP16 and if TRT LLM optimization is applied correctly. Also cross reference with other users who achieved higher RTF on L20.
Tech stack
pythonpytorchdocker
Domain
backendai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
DockerGPU drivers
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50