NVIDIA / NVIDIA/TensorRT-LLM

[Bug]: AutoDeploy: Investigate support for Llama 4 models

Open
#14,015 0 comments 0 reactions 1 assignee View on GitHub

@bmarimuthu-nv is already working on this.

Since May 12, 2026.

AutoDeploy
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

AutoDeploy support for Llama 4 models is currently unknown and needs investigation.

Skipped models:

  • meta-llama/Llama-4-Scout-17B-16E-Instruct
  • meta-llama/Llama-4-Maverick-17B-128E-Instruct
  • meta-llama/Llama-4-Scout-17B-16E
  • meta-llama/Llama-4-Maverick-17B-128E

Reproduce on cw-dfw with:

python examples/auto_deploy/build_and_run_ad.py --model <model id from above> --use-registry

Also monitor the AutoDeploy dashboard for status changes:
https://autodeploy-dashboard-a68618.gitlab-master-pages.nvidia.com/

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.