TensorRT 10.5 Flux-dev torch.float16 precision
Open
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
When I used TensorRT 10.5 to infer Flux-dev on A800 using torch.float16 dataType, I found that there was a significant decrease in accuracy, while there was no significant decrease in accuracy when I used Pytorch torch.float16 and BF16 to infer;especially, I found the T5Model significant decrease in accuracy using torch.float16 dataType;
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is identified in the issue. Start by reproducing the Flux-dev and T5Model precision comparison described for TensorRT 10.5 on an A800, then identify the relevant TensorRT inference path; done requires determining why torch.float16 accuracy differs from PyTorch and BF16.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, pytorch
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100