Support exporting fp4 models

Assessment

This issue has not been assessed yet.

Description

Getting set up

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.

More from NVIDIA-NeMo/Export-Deploy

• [ALERT] Access to NVIDIA's Self-Hosted Runners is Expiring

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  nvidia-runners

  Difficulty 2/5 1-3 hours Newbie friendliness 35/100

  NVIDIA-NeMo/Export-Deploy#759 · Opened Aug 30, 2026

• Update ED to use Dynamic Inference Engine from MCore

  May be free again @oyilmaz-nvidia claimed this 142 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  NVIDIA-NeMo/Export-Deploy#693 · 1 assignee · Opened May 22, 2026

• Incorrect handling of reasoning traces for nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 in MBridge format

  May be free again @athitten claimed this 142 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  NVIDIA-NeMo/Export-Deploy#682 · 1 comment · 1 assignee · Opened May 22, 2026

• Server returns empty answer when too many tokens requested

  May be free again @athitten claimed this 181 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  NVIDIA-NeMo/Export-Deploy#652 · 1 assignee · Opened Apr 13, 2026

• VLM endpoint fails when there are no images in the request

  May be free again @meatybobby claimed this 213 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  NVIDIA-NeMo/Export-Deploy#632 · 1 assignee · Opened Mar 12, 2026

All issues in NVIDIA-NeMo/Export-Deploy

Similar issues

• [Bug] Google Chat `/setup-files start` fails due to mismatched google-cloud-pubsub pin

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  comp/gateway comp/plugins duplicate P3 type/bug

  Difficulty 2/5 1-3 hours Newbie friendliness 82/100

  NousResearch/hermes-agent#137019 · Opened Oct 12, 2026

  Maintainers usually reply within 1 day

• test_run_flow_simulator.py tests fail due to new updated flow version

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  Difficulty 2/5 1-3 hours Newbie friendliness 72/100

  equinor/ert#14639 · Opened Oct 12, 2026

  Maintainers usually reply within 1 day

• [doc] Fix input shape and output-channel description in avg_pool3d

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bot-triaged module: docs triaged

  Difficulty 1/5 1-3 hours Newbie friendliness 88/100

  pytorch/pytorch#200589 · Opened Oct 12, 2026

  Maintainers usually reply within 1 day

• Add DuplexJev: Batched Speech Decisions Without Decoding

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  new-entry

  Difficulty 2/5 1-3 hours Newbie friendliness 78/100

  BinWang28/audio-ai-hub#194 · Opened Oct 12, 2026

• confluence: a paged listing's links re-encode a parameter they carry, where real carries it as sent

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  fidelity

  Difficulty 2/5 1-3 hours Newbie friendliness 63/100

  brekkylab/backlot#625 · Opened Oct 12, 2026

  Maintainers usually reply within 1 day

More Python issues