Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Kernels:
aws-neuron
/
vit-encoder-neuron-kernels

Kernel card Files Files and versions
xet
Community
3
vit-encoder-neuron-kernels
283 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
jburtoft's picture
jburtoft
v1.5: two images per attention producer pass (LNC=1, <=256 tokens) + fix for <=128-token inputs
90f3d2f 21 days ago
  • build
    v1.5: two images per attention producer pass (LNC=1, <=256 tokens) + fix for <=128-token inputs 21 days ago
  • examples
    v1: NKI kernels for RoPE ViT encoders (DINOv3, V-JEPA2) on Trainium2 26 days ago
  • .gitattributes
    211 Bytes
    v1: NKI kernels for RoPE ViT encoders (DINOv3, V-JEPA2) on Trainium2 26 days ago
  • CHANGELOG.md
    9.85 kB
    v1.5: two images per attention producer pass (LNC=1, <=256 tokens) + fix for <=128-token inputs 21 days ago
  • LICENSE
    11.4 kB
    v1: NKI kernels for RoPE ViT encoders (DINOv3, V-JEPA2) on Trainium2 26 days ago
  • NOTICE
    961 Bytes
    v1: NKI kernels for RoPE ViT encoders (DINOv3, V-JEPA2) on Trainium2 26 days ago
  • README.md
    11 kB
    v1.5: two images per attention producer pass (LNC=1, <=256 tokens) + fix for <=128-token inputs 21 days ago