Back to Home11/18/2025, 4:28:47 PM

Triton-Augment: GPU Kernel Fusion for 5-73x Faster Image/Video Augmentation

1 points
1 comments

Mood

calm

Sentiment

positive

Category

tech

Key topics

GPU Optimization

Image/Video Processing

Triton

The author shares Triton-Augment, a library for faster image/video augmentation using GPU kernel fusion, and receives a positive initial response.

Snapshot generated from the HN discussion

Discussion Activity

Light discussion

First comment

N/A

Peak period

2

Hour 1

Avg / period

2

Comment distribution2 data points

Based on 2 loaded comments

Key moments

  1. 01Story posted

    11/18/2025, 4:28:47 PM

    5h ago

    Step 01
  2. 02First comment

    11/18/2025, 4:28:47 PM

    0s after posting

    Step 02
  3. 03Peak activity

    2 comments in Hour 1

    Hottest window of the conversation

    Step 03
  4. 04Latest activity

    11/18/2025, 4:33:02 PM

    5h ago

    Step 04

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (1 comments)
Showing 2 comments
seedlingfl
5h ago
I just released v0.2.0 of Triton-Augment, a PyTorch library to eliminate the GPU data augmentation bottleneck.

The core issue is the "Global Memory Tax": Sequential transforms (Crop, Jitter, Normalize) force the GPU to repeatedly read/write intermediate tensors to VRAM. This kills performance.

The Solution: I use Triton to fuse the entire augmentation pipeline into a single, highly-optimized GPU kernel. This eliminates all intermediate memory I/O.

The Results:

Video: Up to 73.7x faster than Kornia on 5D video tensors.

Image: 8.1x average speedup (up to 12x) over Torchvision v2.

It's designed as a drop-in replacement for your existing Compose pipeline. Check out the GitHub repository for the full API and detailed benchmarks.

I'm focused on developing the next phase (Resize, Rotation, etc.) and welcome any feedback on the kernels or usage patterns!

GitHub: https://github.com/yuhezhang-ai/triton-augment

seedlingfl
5h ago
Hi everyone, I wanted to share a small library that I've been working on: Triton-Augment. Full technical details in the comments
ID: 45968400Type: storyLast synced: 11/18/2025, 4:29:49 PM

Want the full context?

Jump to the original sources

Read the primary article or dive into the live Hacker News thread when you're ready.