NVIDIA / NVIDIA/apex

Not able to observe any speedup on a Nvidia T4 (Turing arch)

Open
#533 4 comments 2 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 trained a model with the fast mixed precision using amp, pytorch on a RTX 2070. I am now trying to run inference on the network on a NVIDIA T4 and I am not able to observe any speedup.
On checking the state_dict of the checkpoint it looks like they are all Torch.Tensors and not Torch.HalfTensor. I can see that the size of the model is smaller in Mixed Precision version than FP32. In order to run inference I just loaded the amp state dict and did an amp initialize. Is there anything else I had to do in order for it to run in FP16?

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

Start by reproducing the reported inference setup on an NVIDIA T4: load the AMP checkpoint, call AMP initialization, and compare it with FP32 inference. Inspect how the state_dict and AMP initialization affect inference precision; done means determining whether additional setup is required and explaining the absence of speedup.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.