[Feature]: AutoDeploy: combined per-transform visualization
Open
@karthikvetrivel is already working on this.
Since Jan 13, 2026.
AutoDeploy
feature request
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
- https://github.com/NVIDIA/TensorRT-LLM/pull/10117 adds static visualization
- https://github.com/NVIDIA/TensorRT-LLM/pull/10150 reviewes the GUI-based visualization from model explorer
Let's combine both visualization such that
- they can be configured together
- they can be turned on / off for each transform
- they are controlled/called in the same place (call function of base transform)
Note this comment as well: https://github.com/NVIDIA/TensorRT-LLM/pull/10117/changes#r2676424422
Assigned to @karthikvetrivel
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.
Assessment
This issue has not been assessed yet.