NVIDIA / NVIDIA/apex

could apex be used in model inference in a way of FP16 with a model trained with FP32 datatype which not use apex in training processure?

Open
#809 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9k
Forks
1.5k
Avg merge
2d 4h
Merged PRs (30d)
3

Description

I have a model trained with a normal training processure without apex. Could I add apex into my inference stage ,or should I first convert my model to FP16 datatype?

Contributor guide

No contributing guide indexed for this repository

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 files, tests, or entry points are identified in the issue. Start by reviewing Apex's mixed-precision inference support and how it handles models trained with FP32, then determine whether inference can use FP16 directly or requires conversion; done means documenting the supported procedure and any required model changes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.