NVIDIA / NVIDIA/TensorRT

Why didn't covert t5xxl into engine in sd3 pipeline?

Open
#4,135 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Module:Demo triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

Thanks for the awesome demo🙏 But when I using the demo by: python3 demo_txt2img_sd3.py "A vibrant street wall covered in colorful graffiti, the centerpiece spells "SD3 MEDIUM", in a storm of colors" --version sd3 --hf-token=$HF_TOKEN

found in /path/TensorRT/demo/Diffusion/stable_diffusion_3_pipeline.py

self.torch_fallback = dict(zip(model_names, [self.torch_inference or model_name in ('t5xxl') for model_name in model_names]))

Why just leave the t5xxl in torch? THX in advance.🙏

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by running the documented demo command and reading demo/Diffusion/stable_diffusion_3_pipeline.py, especially the torch_fallback assignment for t5xxl. Trace how model_names and engine conversion are handled, then establish whether t5xxl can be supported by the TensorRT engine path; completion would require an explicit implementation or rationale.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.