NVIDIA / NVIDIA/TensorRT-Edge-LLM

Question: Why is BF16 data type not supported?

Open
#54 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
563
Forks
135
Avg merge
14h 13m
Merged PRs (30d)
1

Description

I noticed that the current implementation only supports FP16 data type. Could
you explain why BF16 (bfloat16) is not supported? Are there any technical
constraints, or is BF16 support planned for future releases?

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

No file, test, or entry point is named. Start by locating the implementation and documentation that describe supported data types, then check the project’s stated hardware or runtime constraints. Done means documenting why BF16 is unavailable and whether support is planned, if that information can be established.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.