Skip to content

AllenJWZhu/ViT_TensorRT_Inference_Optimization

View on GitHub ↗Related repositories →

Inference optimization of the BERT model using TensorRT, NVIDIA's high-performance deep learning inference platform. TensorRT is designed to maximize the efficiency of deep learning models during inference, particularly on NVIDIA GPUs. By integrating TensorRT with ViT, we aim to significantly enhance the speed, efficiency, and performance of ViT

active 2024-07-212024-08-17 (UTC)

Partial coverage20,541 / 26,297 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
20
Pushes
12
Pull requests
0
Issues
0
Stars
2
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 28 days from 2024-07-21 to 2024-08-17. Pushes: 12 total, peak 8 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 2 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
AllenJWZhu121200

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.