hzwer / hzwer/Practical-RIFE

Support for Multi-GPU?

Open
#111 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1k
Forks
131
PR merge metrics
No merged PRs in 30d

Description

Hi! Amazing repo with very easy to use code and instructions. Thank you for sharing this with the community!

I was wondering if there will be support for multi-gpu in the future for frame interpolation (and potentially super resolution once SAFA is complete). Maybe something using torch.nn.Parallel?

I'm currently using 2 RTX 3090 with a AMD Ryzen 9 5950X 16-Core Processor - processing time on a video for frame interpolation is roughtly 50% of the total duration with model 4.18 for general video content. Eg. 30min video processed in ~15 mins.

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

The request concerns multi-GPU frame interpolation and mentions torch.nn.Parallel, but names no files, tests, or entry points. Begin by locating the frame-interpolation execution path and reviewing how the model currently uses a device. Done would require an agreed multi-GPU design, implementation scope, and validation of processing behavior across two GPUs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.